Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Satinder Singh 0001
@article{DBLP:journals/corr/abs-2402-15391,
author = {Jake Bruce and
Michael Dennis and
Ashley Edwards and
Jack Parker{-}Holder and
Yuge Shi and
Edward Hughes and
Matthew Lai and
Aditi Mavalankar and
Richie Steigerwald and
Chris Apps and
Yusuf Aytar and
Sarah Bechtle and
Feryal M. P. Behbahani and
Stephanie Chan and
Nicolas Heess and
Lucy Gonzalez and
Simon Osindero and
Sherjil Ozair and
Scott E. Reed and
Jingwei Zhang and
Konrad Zolna and
Jeff Clune and
Nando de Freitas and
Satinder Singh and
Tim Rockt{\"{a}}schel},
title = {Genie: Generative Interactive Environments},
journal = {CoRR},
volume = {abs/2402.15391},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.15391},
doi = {10.48550/ARXIV.2402.15391},
eprinttype = {arXiv},
eprint = {2402.15391},
timestamp = {Fri, 22 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-15391.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ai/ZhangDS23,
author = {Qi Zhang and
Edmund H. Durfee and
Satinder Singh},
title = {Risk-aware analysis for interpretations of probabilistic achievement
and maintenance commitments},
journal = {Artif. Intell.},
volume = {317},
pages = {103864},
year = {2023},
url = {https://doi.org/10.1016/j.artint.2023.103864},
doi = {10.1016/J.ARTINT.2023.103864},
timestamp = {Sat, 11 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ai/ZhangDS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gecco/LangeSCZD00F23,
author = {Robert Tjarko Lange and
Tom Schaul and
Yutian Chen and
Tom Zahavy and
Valentin Dalibard and
Chris Lu and
Satinder Singh and
Sebastian Flennerhag},
editor = {Sara Silva and
Lu{\'{\i}}s Paquete},
title = {Discovering Evolution Strategies via Meta-Black-Box Optimization},
booktitle = {Companion Proceedings of the Conference on Genetic and Evolutionary
Computation, {GECCO} 2023, Companion Volume, Lisbon, Portugal, July
15-19, 2023},
pages = {29--30},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3583133.3595822},
doi = {10.1145/3583133.3595822},
timestamp = {Sat, 16 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/gecco/LangeSCZD00F23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/CarvalhoFLL023,
author = {Wilka Carvalho and
Angelos Filos and
Richard L. Lewis and
Honglak Lee and
Satinder Singh},
title = {Composing Task Knowledge With Modular Successor Feature Approximators},
booktitle = {The Eleventh International Conference on Learning Representations,
{ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
year = {2023},
url = {https://openreview.net/pdf?id=DrtSx1z40Ib},
timestamp = {Fri, 30 Jun 2023 14:38:38 +0200},
biburl = {https://dblp.org/rec/conf/iclr/CarvalhoFLL023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/LangeSCZD00F23,
author = {Robert Tjarko Lange and
Tom Schaul and
Yutian Chen and
Tom Zahavy and
Valentin Dalibard and
Chris Lu and
Satinder Singh and
Sebastian Flennerhag},
title = {Discovering Evolution Strategies via Meta-Black-Box Optimization},
booktitle = {The Eleventh International Conference on Learning Representations,
{ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
year = {2023},
url = {https://openreview.net/pdf?id=mFDU0fP3EQH},
timestamp = {Sat, 16 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iclr/LangeSCZD00F23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/LaskinWOPSSSHFB23,
author = {Michael Laskin and
Luyu Wang and
Junhyuk Oh and
Emilio Parisotto and
Stephen Spencer and
Richie Steigerwald and
DJ Strouse and
Steven Stenberg Hansen and
Angelos Filos and
Ethan A. Brooks and
Maxime Gazeau and
Himanshu Sahni and
Satinder Singh and
Volodymyr Mnih},
title = {In-context Reinforcement Learning with Algorithm Distillation},
booktitle = {The Eleventh International Conference on Learning Representations,
{ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
year = {2023},
url = {https://openreview.net/pdf?id=hy0a5MMPUv},
timestamp = {Fri, 30 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/LaskinWOPSSSHFB23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/ZahavySBBFH023,
author = {Tom Zahavy and
Yannick Schroecker and
Feryal M. P. Behbahani and
Kate Baumli and
Sebastian Flennerhag and
Shaobo Hou and
Satinder Singh},
title = {Discovering Policies with DOMiNO: Diversity Optimization Maintaining
Near Optimality},
booktitle = {The Eleventh International Conference on Learning Representations,
{ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
year = {2023},
url = {https://openreview.net/pdf?id=kjkdzBW3b8p},
timestamp = {Fri, 30 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/ZahavySBBFH023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/BauerBBBBCCCDGG23,
author = {Jakob Bauer and
Kate Baumli and
Feryal M. P. Behbahani and
Avishkar Bhoopchand and
Nathalie Bradley{-}Schmieg and
Michael Chang and
Natalie Clay and
Adrian Collister and
Vibhavari Dasagi and
Lucy Gonzalez and
Karol Gregor and
Edward Hughes and
Sheleem Kashem and
Maria Loks{-}Thompson and
Hannah Openshaw and
Jack Parker{-}Holder and
Shreya Pathak and
Nicolas Perez Nieves and
Nemanja Rakicevic and
Tim Rockt{\"{a}}schel and
Yannick Schroecker and
Satinder Singh and
Jakub Sygnowski and
Karl Tuyls and
Sarah York and
Alexander Zacherl and
Lei M. Zhang},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Human-Timescale Adaptation in an Open-Ended Task Space},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {1887--1935},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/bauer23a.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/BauerBBBBCCCDGG23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MoskovitzOVF0Z23,
author = {Ted Moskovitz and
Brendan O'Donoghue and
Vivek Veeriah and
Sebastian Flennerhag and
Satinder Singh and
Tom Zahavy},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for
Last-Iterate Convergence in Constrained MDPs},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {25303--25336},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/moskovitz23a.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MoskovitzOVF0Z23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/0001SGPF0B23,
author = {Chris Lu and
Yannick Schroecker and
Albert Gu and
Emilio Parisotto and
Jakob N. Foerster and
Satinder Singh and
Feryal M. P. Behbahani},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Structured State Space Models for In-Context Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/92d3d2a9801211ca3693ccb2faa1316f-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/0001SGPF0B23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BrooksWL023,
author = {Ethan A. Brooks and
Logan Walls and
Richard L. Lewis and
Satinder Singh},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Large Language Models can Implement Policy Iteration},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/60dc7fa827f5f761ad481e2ad40b5573-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/BrooksWL023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Carvalho0FLMLL023,
author = {Wilka Carvalho and
Andre Saraiva and
Angelos Filos and
Andrew K. Lampinen and
Loic Matthey and
Richard L. Lewis and
Honglak Lee and
Satinder Singh and
Danilo Jimenez Rezende and
Daniel Zoran},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Combining Behaviors with the Successor Features Keyboard},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/1f69928210578f4cf5b538a8c8806798-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Carvalho0FLMLL023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-03236,
author = {Sebastian Flennerhag and
Tom Zahavy and
Brendan O'Donoghue and
Hado van Hasselt and
Andr{\'{a}}s Gy{\"{o}}rgy and
Satinder Singh},
title = {Optimistic Meta-Gradients},
journal = {CoRR},
volume = {abs/2301.03236},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.03236},
doi = {10.48550/ARXIV.2301.03236},
eprinttype = {arXiv},
eprint = {2301.03236},
timestamp = {Tue, 10 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-03236.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-12305,
author = {Wilka Carvalho and
Angelos Filos and
Richard L. Lewis and
Honglak Lee and
Satinder Singh},
title = {Composing Task Knowledge with Modular Successor Feature Approximators},
journal = {CoRR},
volume = {abs/2301.12305},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.12305},
doi = {10.48550/ARXIV.2301.12305},
eprinttype = {arXiv},
eprint = {2301.12305},
timestamp = {Wed, 01 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-12305.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-01275,
author = {Ted Moskovitz and
Brendan O'Donoghue and
Vivek Veeriah and
Sebastian Flennerhag and
Satinder Singh and
Tom Zahavy},
title = {ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for
Last-Iterate Convergence in Constrained MDPs},
journal = {CoRR},
volume = {abs/2302.01275},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.01275},
doi = {10.48550/ARXIV.2302.01275},
eprinttype = {arXiv},
eprint = {2302.01275},
timestamp = {Thu, 09 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-01275.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-14451,
author = {Bernardo {\'{A}}vila Pires and
Feryal M. P. Behbahani and
Hubert Soyer and
Kyriacos Nikiforou and
Thomas Keck and
Satinder Singh},
title = {Hierarchical Reinforcement Learning in Complex 3D Environments},
journal = {CoRR},
volume = {abs/2302.14451},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.14451},
doi = {10.48550/ARXIV.2302.14451},
eprinttype = {arXiv},
eprint = {2302.14451},
timestamp = {Fri, 03 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-14451.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-03982,
author = {Chris Lu and
Yannick Schroecker and
Albert Gu and
Emilio Parisotto and
Jakob N. Foerster and
Satinder Singh and
Feryal M. P. Behbahani},
title = {Structured State Space Models for In-Context Reinforcement Learning},
journal = {CoRR},
volume = {abs/2303.03982},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.03982},
doi = {10.48550/ARXIV.2303.03982},
eprinttype = {arXiv},
eprint = {2303.03982},
timestamp = {Tue, 18 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-03982.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-11044,
author = {David Abel and
Andr{\'{e}} Barreto and
Hado van Hasselt and
Benjamin Van Roy and
Doina Precup and
Satinder Singh},
title = {On the Convergence of Bounded Agents},
journal = {CoRR},
volume = {abs/2307.11044},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.11044},
doi = {10.48550/ARXIV.2307.11044},
eprinttype = {arXiv},
eprint = {2307.11044},
timestamp = {Wed, 26 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-11044.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-11046,
author = {David Abel and
Andr{\'{e}} Barreto and
Benjamin Van Roy and
Doina Precup and
Hado van Hasselt and
Satinder Singh},
title = {A Definition of Continual Reinforcement Learning},
journal = {CoRR},
volume = {abs/2307.11046},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.11046},
doi = {10.48550/ARXIV.2307.11046},
eprinttype = {arXiv},
eprint = {2307.11046},
timestamp = {Wed, 26 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-11046.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-09175,
author = {Tom Zahavy and
Vivek Veeriah and
Shaobo Hou and
Kevin Waugh and
Matthew Lai and
Edouard Leurent and
Nenad Tomasev and
Lisa Schut and
Demis Hassabis and
Satinder Singh},
title = {Diversifying {AI:} Towards Creative Chess with AlphaZero},
journal = {CoRR},
volume = {abs/2308.09175},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.09175},
doi = {10.48550/ARXIV.2308.09175},
eprinttype = {arXiv},
eprint = {2308.09175},
timestamp = {Fri, 25 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-09175.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-15940,
author = {Wilka Carvalho and
Andre Saraiva and
Angelos Filos and
Andrew Kyle Lampinen and
Loic Matthey and
Richard L. Lewis and
Honglak Lee and
Satinder Singh and
Danilo J. Rezende and
Daniel Zoran},
title = {Combining Behaviors with the Successor Features Keyboard},
journal = {CoRR},
volume = {abs/2310.15940},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.15940},
doi = {10.48550/ARXIV.2310.15940},
eprinttype = {arXiv},
eprint = {2310.15940},
timestamp = {Tue, 31 Oct 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-15940.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZhengVL022,
author = {Zeyu Zheng and
Risto Vuorio and
Richard L. Lewis and
Satinder Singh},
title = {Adaptive Pairwise Weights for Temporal Credit Assignment},
booktitle = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
- March 1, 2022},
pages = {9225--9232},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i8.20909},
doi = {10.1609/AAAI.V36I8.20909},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZhengVL022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/collas/LuketinaFSAZ022,
author = {Jelena Luketina and
Sebastian Flennerhag and
Yannick Schroecker and
David Abel and
Tom Zahavy and
Satinder Singh},
editor = {Sarath Chandar and
Razvan Pascanu and
Doina Precup},
title = {Meta-Gradients in Non-Stationary Environments},
booktitle = {Conference on Lifelong Learning Agents, CoLLAs 2022, 22-24 August
2022, McGill University, Montr{\'{e}}al, Qu{\'{e}}bec, Canada},
series = {Proceedings of Machine Learning Research},
volume = {199},
pages = {886--901},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v199/luketina22a.html},
timestamp = {Fri, 17 Feb 2023 16:29:10 +0100},
biburl = {https://dblp.org/rec/conf/collas/LuketinaFSAZ022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/FlennerhagSZHS022,
author = {Sebastian Flennerhag and
Yannick Schroecker and
Tom Zahavy and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Bootstrapped Meta-Learning},
booktitle = {The Tenth International Conference on Learning Representations, {ICLR}
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=b-ny3x071E5},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/FlennerhagSZHS022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/AbelDHHLP022,
author = {David Abel and
Will Dabney and
Anna Harutyunyan and
Mark K. Ho and
Michael L. Littman and
Doina Precup and
Satinder Singh},
editor = {Luc De Raedt},
title = {On the Expressivity of Markov Reward (Extended Abstract)},
booktitle = {Proceedings of the Thirty-First International Joint Conference on
Artificial Intelligence, {IJCAI} 2022, Vienna, Austria, 23-29 July
2022},
pages = {5254--5258},
publisher = {ijcai.org},
year = {2022},
url = {https://doi.org/10.24963/ijcai.2022/730},
doi = {10.24963/IJCAI.2022/730},
timestamp = {Wed, 27 Jul 2022 16:43:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/AbelDHHLP022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Arumugam022,
author = {Dilip Arumugam and
Satinder Singh},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Planning to the Information Horizon of BAMDPs via Epistemic State
Abstraction},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/80b7bec60081f95d900973509744a306-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Arumugam022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GrimmBS22,
author = {Christopher Grimm and
Andr{\'{e}} Barreto and
Satinder Singh},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Approximate Value Equivalence},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/d53538ba21c05fa361d2b21704172753-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/GrimmBS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LiuZM022,
author = {Hao Liu and
Tom Zahavy and
Volodymyr Mnih and
Satinder Singh},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Palm up: Playing in the Latent Manifold for Unsupervised Pretraining},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/e92381dba235a8309f08ce46376189a9-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/LiuZM022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-04772,
author = {Vivek Veeriah and
Zeyu Zheng and
Richard L. Lewis and
Satinder Singh},
title = {GrASP: Gradient-Based Affordance Selection for Planning},
journal = {CoRR},
volume = {abs/2202.04772},
year = {2022},
url = {https://arxiv.org/abs/2202.04772},
eprinttype = {arXiv},
eprint = {2202.04772},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-04772.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-13521,
author = {Tom Zahavy and
Yannick Schroecker and
Feryal M. P. Behbahani and
Kate Baumli and
Sebastian Flennerhag and
Shaobo Hou and
Satinder Singh},
title = {Discovering Policies with DOMiNO: Diversity Optimization Maintaining
Near Optimality},
journal = {CoRR},
volume = {abs/2205.13521},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.13521},
doi = {10.48550/ARXIV.2205.13521},
eprinttype = {arXiv},
eprint = {2205.13521},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-13521.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-15378,
author = {Julien P{\'{e}}rolat and
Bart De Vylder and
Daniel Hennes and
Eugene Tarassov and
Florian Strub and
Vincent de Boer and
Paul Muller and
Jerome T. Connor and
Neil Burch and
Thomas W. Anthony and
Stephen McAleer and
Romuald Elie and
Sarah H. Cen and
Zhe Wang and
Audrunas Gruslys and
Aleksandra Malysheva and
Mina Khan and
Sherjil Ozair and
Finbarr Timbers and
Toby Pohlen and
Tom Eccles and
Mark Rowland and
Marc Lanctot and
Jean{-}Baptiste Lespiau and
Bilal Piot and
Shayegan Omidshafiei and
Edward Lockhart and
Laurent Sifre and
Nathalie Beauguerlange and
R{\'{e}}mi Munos and
David Silver and
Satinder Singh and
Demis Hassabis and
Karl Tuyls},
title = {Mastering the Game of Stratego with Model-Free Multiagent Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2206.15378},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.15378},
doi = {10.48550/ARXIV.2206.15378},
eprinttype = {arXiv},
eprint = {2206.15378},
timestamp = {Wed, 28 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-15378.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-06159,
author = {Jelena Luketina and
Sebastian Flennerhag and
Yannick Schroecker and
David Abel and
Tom Zahavy and
Satinder Singh},
title = {Meta-Gradients in Non-Stationary Environments},
journal = {CoRR},
volume = {abs/2209.06159},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.06159},
doi = {10.48550/ARXIV.2209.06159},
eprinttype = {arXiv},
eprint = {2209.06159},
timestamp = {Tue, 27 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-06159.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-03821,
author = {Ethan A. Brooks and
Logan Walls and
Richard L. Lewis and
Satinder Singh},
title = {In-Context Policy Iteration},
journal = {CoRR},
volume = {abs/2210.03821},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.03821},
doi = {10.48550/ARXIV.2210.03821},
eprinttype = {arXiv},
eprint = {2210.03821},
timestamp = {Wed, 12 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-03821.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-10913,
author = {Hao Liu and
Tom Zahavy and
Volodymyr Mnih and
Satinder Singh},
title = {Palm up: Playing in the Latent Manifold for Unsupervised Pretraining},
journal = {CoRR},
volume = {abs/2210.10913},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.10913},
doi = {10.48550/ARXIV.2210.10913},
eprinttype = {arXiv},
eprint = {2210.10913},
timestamp = {Tue, 25 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-10913.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-14215,
author = {Michael Laskin and
Luyu Wang and
Junhyuk Oh and
Emilio Parisotto and
Stephen Spencer and
Richie Steigerwald and
DJ Strouse and
Steven Hansen and
Angelos Filos and
Ethan A. Brooks and
Maxime Gazeau and
Himanshu Sahni and
Satinder Singh and
Volodymyr Mnih},
title = {In-context Reinforcement Learning with Algorithm Distillation},
journal = {CoRR},
volume = {abs/2210.14215},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.14215},
doi = {10.48550/ARXIV.2210.14215},
eprinttype = {arXiv},
eprint = {2210.14215},
timestamp = {Wed, 19 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-14215.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-16872,
author = {Dilip Arumugam and
Satinder Singh},
title = {Planning to the Information Horizon of BAMDPs via Epistemic State
Abstraction},
journal = {CoRR},
volume = {abs/2210.16872},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.16872},
doi = {10.48550/ARXIV.2210.16872},
eprinttype = {arXiv},
eprint = {2210.16872},
timestamp = {Fri, 09 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-16872.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-11260,
author = {Robert Tjarko Lange and
Tom Schaul and
Yutian Chen and
Tom Zahavy and
Valentin Dallibard and
Chris Lu and
Satinder Singh and
Sebastian Flennerhag},
title = {Discovering Evolution Strategies via Meta-Black-Box Optimization},
journal = {CoRR},
volume = {abs/2211.11260},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.11260},
doi = {10.48550/ARXIV.2211.11260},
eprinttype = {arXiv},
eprint = {2211.11260},
timestamp = {Sat, 16 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-11260.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-14530,
author = {Khimya Khetarpal and
Claire Vernade and
Brendan O'Donoghue and
Satinder Singh and
Tom Zahavy},
title = {{POMRL:} No-Regret Learning-to-Plan with Increasing Horizons},
journal = {CoRR},
volume = {abs/2212.14530},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.14530},
doi = {10.48550/ARXIV.2212.14530},
eprinttype = {arXiv},
eprint = {2212.14530},
timestamp = {Sun, 08 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-14530.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ai/SilverSPS21,
author = {David Silver and
Satinder Singh and
Doina Precup and
Richard S. Sutton},
title = {Reward is enough},
journal = {Artif. Intell.},
volume = {299},
pages = {103535},
year = {2021},
url = {https://doi.org/10.1016/j.artint.2021.103535},
doi = {10.1016/J.ARTINT.2021.103535},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ai/SilverSPS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/0038DS21,
author = {Qi Zhang and
Edmund H. Durfee and
Satinder Singh},
title = {Efficient Querying for Cooperative Probabilistic Commitments},
booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI}
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9,
2021},
pages = {11378--11386},
publisher = {{AAAI} Press},
year = {2021},
url = {https://doi.org/10.1609/aaai.v35i13.17356},
doi = {10.1609/AAAI.V35I13.17356},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/0038DS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/ZahavyBMHOKS21,
author = {Tom Zahavy and
Andr{\'{e}} Barreto and
Daniel J. Mankowitz and
Shaobo Hou and
Brendan O'Donoghue and
Iurii Kemaev and
Satinder Singh},
title = {Discovering a set of policies for the worst case reward},
booktitle = {9th International Conference on Learning Representations, {ICLR} 2021,
Virtual Event, Austria, May 3-7, 2021},
publisher = {OpenReview.net},
year = {2021},
url = {https://openreview.net/forum?id=PUkhWz65dy5},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/ZahavyBMHOKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/BrooksRLS21,
author = {Ethan A. Brooks and
Janarthanan Rajendran and
Richard L. Lewis and
Satinder Singh},
editor = {Marina Meila and
Tong Zhang},
title = {Reinforcement Learning of Implicit and Explicit Control Flow Instructions},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {1082--1091},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/brooks21a.html},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/BrooksRLS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/CarvalhoLLSLLS21,
author = {Wilka Carvalho and
Anthony Liang and
Kimin Lee and
Sungryull Sohn and
Honglak Lee and
Richard L. Lewis and
Satinder Singh},
editor = {Zhi{-}Hua Zhou},
title = {Reinforcement Learning for Sparse-Reward Object-Interaction Tasks
in a First-person Simulated 3D Environment},
booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial
Intelligence, {IJCAI} 2021, Virtual Event / Montreal, Canada, 19-27
August 2021},
pages = {2219--2226},
publisher = {ijcai.org},
year = {2021},
url = {https://doi.org/10.24963/ijcai.2021/306},
doi = {10.24963/IJCAI.2021/306},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/CarvalhoLLSLLS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GrimmBFSS21,
author = {Christopher Grimm and
Andr{\'{e}} Barreto and
Gregory Farquhar and
David Silver and
Satinder Singh},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Proper Value Equivalence},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {7773--7786},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/400e5e6a7ce0c754f281525fae75a873-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/GrimmBFSS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AbelDHHLPS21,
author = {David Abel and
Will Dabney and
Anna Harutyunyan and
Mark K. Ho and
Michael L. Littman and
Doina Precup and
Satinder Singh},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {On the Expressivity of Markov Reward},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {7799--7812},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/4079016d940210b4ae9ae7d41c4a2065-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/AbelDHHLPS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZhengVVLS21,
author = {Zeyu Zheng and
Vivek Veeriah and
Risto Vuorio and
Richard L. Lewis and
Satinder Singh},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Learning State Representations from Random Deep Action-conditional
Predictions},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {23679--23691},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/c71df24045cfddab4a963d3ac9bdc9a3-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/ZhengVVLS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZahavyODS21,
author = {Tom Zahavy and
Brendan O'Donoghue and
Guillaume Desjardins and
Satinder Singh},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Reward is enough for convex MDPs},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {25746--25759},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/d7e4cdde82a894b8f633e6d61a01ef15-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/ZahavyODS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/VeeriahZHXOKHSS21,
author = {Vivek Veeriah and
Tom Zahavy and
Matteo Hessel and
Zhongwen Xu and
Junhyuk Oh and
Iurii Kemaev and
Hado van Hasselt and
David Silver and
Satinder Singh},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Discovery of Options via Meta-Learned Subgoals},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {29861--29873},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/fa246d0262c3925617b0c72bb20eeb1d-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/VeeriahZHXOKHSS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-04323,
author = {Tom Zahavy and
Andr{\'{e}} Barreto and
Daniel J. Mankowitz and
Shaobo Hou and
Brendan O'Donoghue and
Iurii Kemaev and
Satinder Singh},
title = {Discovering a set of policies for the worst case reward},
journal = {CoRR},
volume = {abs/2102.04323},
year = {2021},
url = {https://arxiv.org/abs/2102.04323},
eprinttype = {arXiv},
eprint = {2102.04323},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-04323.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-04897,
author = {Zeyu Zheng and
Vivek Veeriah and
Risto Vuorio and
Richard L. Lewis and
Satinder Singh},
title = {Learning State Representations from Random Deep Action-conditional
Predictions},
journal = {CoRR},
volume = {abs/2102.04897},
year = {2021},
url = {https://arxiv.org/abs/2102.04897},
eprinttype = {arXiv},
eprint = {2102.04897},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-04897.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-04999,
author = {Zeyu Zheng and
Risto Vuorio and
Richard L. Lewis and
Satinder Singh},
title = {Pairwise Weights for Temporal Credit Assignment},
journal = {CoRR},
volume = {abs/2102.04999},
year = {2021},
url = {https://arxiv.org/abs/2102.04999},
eprinttype = {arXiv},
eprint = {2102.04999},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-04999.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-06741,
author = {Vivek Veeriah and
Tom Zahavy and
Matteo Hessel and
Zhongwen Xu and
Junhyuk Oh and
Iurii Kemaev and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Discovery of Options via Meta-Learned Subgoals},
journal = {CoRR},
volume = {abs/2102.06741},
year = {2021},
url = {https://arxiv.org/abs/2102.06741},
eprinttype = {arXiv},
eprint = {2102.06741},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-06741.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-13195,
author = {Ethan A. Brooks and
Janarthanan Rajendran and
Richard L. Lewis and
Satinder Singh},
title = {Reinforcement Learning of Implicit and Explicit Control Flow in Instructions},
journal = {CoRR},
volume = {abs/2102.13195},
year = {2021},
url = {https://arxiv.org/abs/2102.13195},
eprinttype = {arXiv},
eprint = {2102.13195},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-13195.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-00661,
author = {Tom Zahavy and
Brendan O'Donoghue and
Guillaume Desjardins and
Satinder Singh},
title = {Reward is enough for convex MDPs},
journal = {CoRR},
volume = {abs/2106.00661},
year = {2021},
url = {https://arxiv.org/abs/2106.00661},
eprinttype = {arXiv},
eprint = {2106.00661},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-00661.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-00669,
author = {Tom Zahavy and
Brendan O'Donoghue and
Andr{\'{e}} Barreto and
Volodymyr Mnih and
Sebastian Flennerhag and
Satinder Singh},
title = {Discovering Diverse Nearly Optimal Policies withSuccessor Features},
journal = {CoRR},
volume = {abs/2106.00669},
year = {2021},
url = {https://arxiv.org/abs/2106.00669},
eprinttype = {arXiv},
eprint = {2106.00669},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-00669.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-10316,
author = {Christopher Grimm and
Andr{\'{e}} Barreto and
Gregory Farquhar and
David Silver and
Satinder Singh},
title = {Proper Value Equivalence},
journal = {CoRR},
volume = {abs/2106.10316},
year = {2021},
url = {https://arxiv.org/abs/2106.10316},
eprinttype = {arXiv},
eprint = {2106.10316},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-10316.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-04504,
author = {Sebastian Flennerhag and
Yannick Schroecker and
Tom Zahavy and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Bootstrapped Meta-Learning},
journal = {CoRR},
volume = {abs/2109.04504},
year = {2021},
url = {https://arxiv.org/abs/2109.04504},
eprinttype = {arXiv},
eprint = {2109.04504},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-04504.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-15724,
author = {Janarthanan Rajendran and
Jonathan K. Kummerfeld and
Satinder Singh},
title = {Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog
Tasks},
journal = {CoRR},
volume = {abs/2110.15724},
year = {2021},
url = {https://arxiv.org/abs/2110.15724},
eprinttype = {arXiv},
eprint = {2110.15724},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-15724.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-00876,
author = {David Abel and
Will Dabney and
Anna Harutyunyan and
Mark K. Ho and
Michael L. Littman and
Doina Precup and
Satinder Singh},
title = {On the Expressivity of Markov Reward},
journal = {CoRR},
volume = {abs/2111.00876},
year = {2021},
url = {https://arxiv.org/abs/2111.00876},
eprinttype = {arXiv},
eprint = {2111.00876},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-00876.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/ZhangDS20,
author = {Qi Zhang and
Edmund H. Durfee and
Satinder Singh},
title = {Semantics and algorithms for trustworthy commitment achievement under
model uncertainty},
journal = {Auton. Agents Multi Agent Syst.},
volume = {34},
number = {1},
pages = {19},
year = {2020},
url = {https://doi.org/10.1007/s10458-020-09443-0},
doi = {10.1007/S10458-020-09443-0},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aamas/ZhangDS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZhangDS20,
author = {Shun Zhang and
Edmund H. Durfee and
Satinder Singh},
title = {Querying to Find a Safe Policy under Uncertain Safety Constraints
in Markov Decision Processes},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {2552--2559},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i03.5638},
doi = {10.1609/AAAI.V34I03.5638},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZhangDS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/RajendranLVLS20,
author = {Janarthanan Rajendran and
Richard L. Lewis and
Vivek Veeriah and
Honglak Lee and
Satinder Singh},
title = {How Should an Agent Practice?},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {5454--5461},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i04.5995},
doi = {10.1609/AAAI.V34I04.5995},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/RajendranLVLS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/0038DS20,
author = {Qi Zhang and
Edmund H. Durfee and
Satinder Singh},
title = {Modeling Probabilistic Commitments for Maintenance Is Inherently Harder
than for Achievement},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {10326--10333},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i06.6596},
doi = {10.1609/AAAI.V34I06.6596},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/0038DS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/0002JTS20,
author = {Aditya Modi and
Nan Jiang and
Ambuj Tewari and
Satinder Singh},
editor = {Silvia Chiappa and
Roberto Calandra},
title = {Sample Complexity of Reinforcement Learning using Linearly Combined
Model Ensembles},
booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]},
series = {Proceedings of Machine Learning Research},
volume = {108},
pages = {2010--2020},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v108/modi20a.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/0002JTS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/OsbandDHASSMLSS20,
author = {Ian Osband and
Yotam Doron and
Matteo Hessel and
John Aslanides and
Eren Sezener and
Andre Saraiva and
Katrina McKinney and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Satinder Singh and
Benjamin Van Roy and
Richard S. Sutton and
David Silver and
Hado van Hasselt},
title = {Behaviour Suite for Reinforcement Learning},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=rygf-kSYwH},
timestamp = {Mon, 15 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/OsbandDHASSMLSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhengOHXKHSS20,
author = {Zeyu Zheng and
Junhyuk Oh and
Matteo Hessel and
Zhongwen Xu and
Manuel Kroiss and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {What Can Learned Intrinsic Rewards Capture?},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {11436--11446},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/zheng20b.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZhengOHXKHSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AnthonyETKGHPLP20,
author = {Thomas W. Anthony and
Tom Eccles and
Andrea Tacchetti and
J{\'{a}}nos Kram{\'{a}}r and
Ian Gemp and
Thomas C. Hudson and
Nicolas Porcel and
Marc Lanctot and
Julien P{\'{e}}rolat and
Richard Everett and
Satinder Singh and
Thore Graepel and
Yoram Bachrach},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Learning to Play No-Press Diplomacy with Best Response Policy Iteration},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/d1419302db9c022ab1d48681b13d5f8b-Abstract.html},
timestamp = {Wed, 06 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/AnthonyETKGHPLP20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GrimmBSS20,
author = {Christopher Grimm and
Andr{\'{e}} Barreto and
Satinder Singh and
David Silver},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {The Value Equivalence Principle for Model-Based Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/3bb585ea00014b0e3ebe4c6dd165a358-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/GrimmBSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/OhHCXHSS20,
author = {Junhyuk Oh and
Matteo Hessel and
Wojciech M. Czarnecki and
Zhongwen Xu and
Hado van Hasselt and
Satinder Singh and
David Silver},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Discovering Reinforcement Learning Algorithms},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/0b96d81f0494fde5428c7aea243c9157-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/OhHCXHSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WenPIBRS20,
author = {Zheng Wen and
Doina Precup and
Morteza Ibrahimi and
Andr{\'{e}} Barreto and
Benjamin Van Roy and
Satinder Singh},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {On Efficiency in Hierarchical Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/4a5cfa9281924139db466a8a19291aff-Abstract.html},
timestamp = {Thu, 31 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/WenPIBRS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/XuHHOSS20,
author = {Zhongwen Xu and
Hado Philip van Hasselt and
Matteo Hessel and
Junhyuk Oh and
Satinder Singh and
David Silver},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Meta-Gradient Reinforcement Learning with an Objective Discovered
Online},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/ae3d525daf92cee0003a7f2d92c34ea3-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/XuHHOSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZahavyXVHOHSS20,
author = {Tom Zahavy and
Zhongwen Xu and
Vivek Veeriah and
Matteo Hessel and
Junhyuk Oh and
Hado van Hasselt and
David Silver and
Satinder Singh},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {A Self-Tuning Actor-Critic Algorithm},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/f02208a057804ee16ac72ff4d3cec53b-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/ZahavyXVHOHSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-12928,
author = {Tom Zahavy and
Zhongwen Xu and
Vivek Veeriah and
Matteo Hessel and
Junhyuk Oh and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Self-Tuning Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/2002.12928},
year = {2020},
url = {https://arxiv.org/abs/2002.12928},
eprinttype = {arXiv},
eprint = {2002.12928},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-12928.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-04635,
author = {Thomas W. Anthony and
Tom Eccles and
Andrea Tacchetti and
J{\'{a}}nos Kram{\'{a}}r and
Ian Gemp and
Thomas C. Hudson and
Nicolas Porcel and
Marc Lanctot and
Julien P{\'{e}}rolat and
Richard Everett and
Satinder Singh and
Thore Graepel and
Yoram Bachrach},
title = {Learning to Play No-Press Diplomacy with Best Response Policy Iteration},
journal = {CoRR},
volume = {abs/2006.04635},
year = {2020},
url = {https://arxiv.org/abs/2006.04635},
eprinttype = {arXiv},
eprint = {2006.04635},
timestamp = {Wed, 06 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-04635.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-08433,
author = {Zhongwen Xu and
Hado van Hasselt and
Matteo Hessel and
Junhyuk Oh and
Satinder Singh and
David Silver},
title = {Meta-Gradient Reinforcement Learning with an Objective Discovered
Online},
journal = {CoRR},
volume = {abs/2007.08433},
year = {2020},
url = {https://arxiv.org/abs/2007.08433},
eprinttype = {arXiv},
eprint = {2007.08433},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-08433.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-08794,
author = {Junhyuk Oh and
Matteo Hessel and
Wojciech M. Czarnecki and
Zhongwen Xu and
Hado van Hasselt and
Satinder Singh and
David Silver},
title = {Discovering Reinforcement Learning Algorithms},
journal = {CoRR},
volume = {abs/2007.08794},
year = {2020},
url = {https://arxiv.org/abs/2007.08794},
eprinttype = {arXiv},
eprint = {2007.08794},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-08794.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-15195,
author = {Wilka Carvalho and
Anthony Liang and
Kimin Lee and
Sungryull Sohn and
Honglak Lee and
Richard L. Lewis and
Satinder Singh},
title = {Reinforcement Learning for Sparse-Reward Object-Interaction Tasks
in First-person Simulated 3D Environments},
journal = {CoRR},
volume = {abs/2010.15195},
year = {2020},
url = {https://arxiv.org/abs/2010.15195},
eprinttype = {arXiv},
eprint = {2010.15195},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-15195.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-03506,
author = {Christopher Grimm and
Andr{\'{e}} Barreto and
Satinder Singh and
David Silver},
title = {The Value Equivalence Principle for Model-Based Reinforcement Learning},
journal = {CoRR},
volume = {abs/2011.03506},
year = {2020},
url = {https://arxiv.org/abs/2011.03506},
eprinttype = {arXiv},
eprint = {2011.03506},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-03506.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-07195,
author = {Qi Zhang and
Edmund H. Durfee and
Satinder Singh},
title = {Efficient Querying for Cooperative Probabilistic Commitments},
journal = {CoRR},
volume = {abs/2012.07195},
year = {2020},
url = {https://arxiv.org/abs/2012.07195},
eprinttype = {arXiv},
eprint = {2012.07195},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-07195.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZhangLSD19,
author = {Qi Zhang and
Richard L. Lewis and
Satinder Singh and
Edmund H. Durfee},
title = {Learning to Communicate and Solve Visual Blocks-World Tasks},
booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019},
pages = {5781--5788},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33015781},
doi = {10.1609/AAAI.V33I01.33015781},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZhangLSD19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdm/HollerVQTJJSWY19,
author = {John Holler and
Risto Vuorio and
Zhiwei (Tony) Qin and
Xiaocheng Tang and
Yan Jiao and
Tiancheng Jin and
Satinder Singh and
Chenxi Wang and
Jieping Ye},
editor = {Jianyong Wang and
Kyuseok Shim and
Xindong Wu},
title = {Deep Reinforcement Learning for Multi-driver Vehicle Dispatching and
Repositioning Problem},
booktitle = {2019 {IEEE} International Conference on Data Mining, {ICDM} 2019,
Beijing, China, November 8-11, 2019},
pages = {1090--1095},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICDM.2019.00129},
doi = {10.1109/ICDM.2019.00129},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icdm/HollerVQTJJSWY19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/ZhangDS19,
author = {Qi Zhang and
Edmund H. Durfee and
Satinder Singh},
editor = {Hu{\'{a}}scar Espinoza and
Han Yu and
Xiaowei Huang and
Freddy L{\'{e}}cu{\'{e}} and
Cynthia Chen and
Jos{\'{e}} Hern{\'{a}}ndez{-}Orallo and
Se{\'{a}}n {\'{O}} h{\'{E}}igeartaigh and
Richard Mallah},
title = {Computational Strategies for the Trustworthy Pursuit and the Safe
Modeling of Probabilistic Maintenance Commitments},
booktitle = {Proceedings of the Workshop on Artificial Intelligence Safety 2019
co-located with the 28th International Joint Conference on Artificial
Intelligence, AISafety@IJCAI 2019, Macao, China, August 11-12, 2019},
series = {{CEUR} Workshop Proceedings},
volume = {2419},
publisher = {CEUR-WS.org},
year = {2019},
url = {https://ceur-ws.org/Vol-2419/paper\_8.pdf},
timestamp = {Fri, 10 Mar 2023 16:23:31 +0100},
biburl = {https://dblp.org/rec/conf/ijcai/ZhangDS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/PaquetteLBSOKPS19,
author = {Philip Paquette and
Yuchen Lu and
Steven Bocco and
Max O. Smith and
Satya Ortiz{-}Gagne and
Jonathan K. Kummerfeld and
Joelle Pineau and
Satinder Singh and
Aaron C. Courville},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {No-Press Diplomacy: Modeling Multi-Agent Gameplay},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {4476--4487},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/84b20b1f5a0d103f5710bb67a043cd78-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/PaquetteLBSOKPS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/VeeriahHXRLOHSS19,
author = {Vivek Veeriah and
Matteo Hessel and
Zhongwen Xu and
Janarthanan Rajendran and
Richard L. Lewis and
Junhyuk Oh and
Hado van Hasselt and
David Silver and
Satinder Singh},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Discovery of Useful Questions as Auxiliary Tasks},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {9306--9317},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/10ff0b5e85e5b85cc3095d431d8c08b4-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/VeeriahHXRLOHSS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HarutyunyanDMAP19,
author = {Anna Harutyunyan and
Will Dabney and
Thomas Mesnard and
Mohammad Gheshlaghi Azar and
Bilal Piot and
Nicolas Heess and
Hado van Hasselt and
Gregory Wayne and
Satinder Singh and
Doina Precup and
R{\'{e}}mi Munos},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Hindsight Credit Assignment},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {12467--12476},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/195f15384c2a79cedf293e4a847ce85c-Abstract.html},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/HarutyunyanDMAP19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ranlp/RajendranGGYSP19,
author = {Janarthanan Rajendran and
Jatin Ganhotra and
Xiaoxiao Guo and
Mo Yu and
Satinder Singh and
Lazaros Polymenakos},
editor = {Ruslan Mitkov and
Galia Angelova},
title = {NE-Table: {A} Neural key-value table for Named Entities},
booktitle = {Proceedings of the International Conference on Recent Advances in
Natural Language Processing, {RANLP} 2019, Varna, Bulgaria, September
2-4, 2019},
pages = {980--993},
publisher = {{INCOMA} Ltd.},
year = {2019},
url = {https://doi.org/10.26615/978-954-452-056-4\_114},
doi = {10.26615/978-954-452-056-4\_114},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ranlp/RajendranGGYSP19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/lncs/PriestCSA019,
author = {Benjamin W. Priest and
George Cybenko and
Satinder Singh and
Massimiliano Albanese and
Peng Liu},
editor = {Sushil Jajodia and
George Cybenko and
Peng Liu and
Cliff Wang and
Michael P. Wellman},
title = {Online and Scalable Adaptive Cyber Defense},
booktitle = {Adversarial and Uncertain Reasoning for Adaptive Cyber Defense - Control-
and Game-Theoretic Approaches to Cyber Security},
series = {Lecture Notes in Computer Science},
volume = {11830},
pages = {232--261},
publisher = {Springer},
year = {2019},
url = {https://doi.org/10.1007/978-3-030-30719-6\_10},
doi = {10.1007/978-3-030-30719-6\_10},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/series/lncs/PriestCSA019.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-08649,
author = {Christopher Grimm and
Satinder Singh},
title = {Learning Independently-Obtainable Reward Functions},
journal = {CoRR},
volume = {abs/1901.08649},
year = {2019},
url = {http://arxiv.org/abs/1901.08649},
eprinttype = {arXiv},
eprint = {1901.08649},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-08649.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-03568,
author = {Ian Osband and
Yotam Doron and
Matteo Hessel and
John Aslanides and
Eren Sezener and
Andre Saraiva and
Katrina McKinney and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Satinder Singh and
Benjamin Van Roy and
Richard S. Sutton and
David Silver and
Hado van Hasselt},
title = {Behaviour Suite for Reinforcement Learning},
journal = {CoRR},
volume = {abs/1908.03568},
year = {2019},
url = {http://arxiv.org/abs/1908.03568},
eprinttype = {arXiv},
eprint = {1908.03568},
timestamp = {Mon, 15 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-03568.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-02128,
author = {Philip Paquette and
Yuchen Lu and
Steven Bocco and
Max O. Smith and
Satya Ortiz{-}Gagne and
Jonathan K. Kummerfeld and
Satinder Singh and
Joelle Pineau and
Aaron C. Courville},
title = {No Press Diplomacy: Modeling Multi-Agent Gameplay},
journal = {CoRR},
volume = {abs/1909.02128},
year = {2019},
url = {http://arxiv.org/abs/1909.02128},
eprinttype = {arXiv},
eprint = {1909.02128},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-02128.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-04607,
author = {Vivek Veeriah and
Matteo Hessel and
Zhongwen Xu and
Richard L. Lewis and
Janarthanan Rajendran and
Junhyuk Oh and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Discovery of Useful Questions as Auxiliary Tasks},
journal = {CoRR},
volume = {abs/1909.04607},
year = {2019},
url = {http://arxiv.org/abs/1909.04607},
eprinttype = {arXiv},
eprint = {1909.04607},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-04607.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-10597,
author = {Aditya Modi and
Nan Jiang and
Ambuj Tewari and
Satinder Singh},
title = {Sample Complexity of Reinforcement Learning using Linearly Combined
Model Ensembles},
journal = {CoRR},
volume = {abs/1910.10597},
year = {2019},
url = {http://arxiv.org/abs/1910.10597},
eprinttype = {arXiv},
eprint = {1910.10597},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-10597.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-14361,
author = {Victor Bapst and
Alvaro Sanchez{-}Gonzalez and
Omar Shams and
Kimberly L. Stachenfeld and
Peter W. Battaglia and
Satinder Singh and
Jessica B. Hamrick},
title = {Object-oriented state editing for {HRL}},
journal = {CoRR},
volume = {abs/1910.14361},
year = {2019},
url = {http://arxiv.org/abs/1910.14361},
eprinttype = {arXiv},
eprint = {1910.14361},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-14361.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-10866,
author = {Christopher Grimm and
Irina Higgins and
Andr{\'{e}} Barreto and
Denis Teplyashin and
Markus Wulfmeier and
Tim Hertweck and
Raia Hadsell and
Satinder Singh},
title = {Disentangled Cumulants Help Successor Representations Transfer to
New Tasks},
journal = {CoRR},
volume = {abs/1911.10866},
year = {2019},
url = {http://arxiv.org/abs/1911.10866},
eprinttype = {arXiv},
eprint = {1911.10866},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-10866.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-11260,
author = {John Holler and
Risto Vuorio and
Zhiwei (Tony) Qin and
Xiaocheng Tang and
Yan Jiao and
Tiancheng Jin and
Satinder Singh and
Chenxi Wang and
Jieping Ye},
title = {Deep Reinforcement Learning for Multi-Driver Vehicle Dispatching and
Repositioning Problem},
journal = {CoRR},
volume = {abs/1911.11260},
year = {2019},
url = {http://arxiv.org/abs/1911.11260},
eprinttype = {arXiv},
eprint = {1911.11260},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-11260.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-02503,
author = {Anna Harutyunyan and
Will Dabney and
Thomas Mesnard and
Mohammad Gheshlaghi Azar and
Bilal Piot and
Nicolas Heess and
Hado van Hasselt and
Greg Wayne and
Satinder Singh and
Doina Precup and
R{\'{e}}mi Munos},
title = {Hindsight Credit Assignment},
journal = {CoRR},
volume = {abs/1912.02503},
year = {2019},
url = {http://arxiv.org/abs/1912.02503},
eprinttype = {arXiv},
eprint = {1912.02503},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-02503.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-05500,
author = {Zeyu Zheng and
Junhyuk Oh and
Matteo Hessel and
Zhongwen Xu and
Manuel Kroiss and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {What Can Learned Intrinsic Rewards Capture?},
journal = {CoRR},
volume = {abs/1912.05500},
year = {2019},
url = {http://arxiv.org/abs/1912.05500},
eprinttype = {arXiv},
eprint = {1912.05500},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-05500.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-07045,
author = {Janarthanan Rajendran and
Richard L. Lewis and
Vivek Veeriah and
Honglak Lee and
Satinder Singh},
title = {How Should an Agent Practice?},
journal = {CoRR},
volume = {abs/1912.07045},
year = {2019},
url = {http://arxiv.org/abs/1912.07045},
eprinttype = {arXiv},
eprint = {1912.07045},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-07045.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/scn/NguyenWWS18,
author = {Thanh Hong Nguyen and
Mason Wright and
Michael P. Wellman and
Satinder Singh},
title = {Multistage Attack Graph Security Games: Heuristic Strategies, with
Empirical Game-Theoretic Analysis},
journal = {Secur. Commun. Networks},
volume = {2018},
pages = {2864873:1--2864873:28},
year = {2018},
url = {https://doi.org/10.1155/2018/2864873},
doi = {10.1155/2018/2864873},
timestamp = {Thu, 07 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/scn/NguyenWWS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/0002JST18,
author = {Aditya Modi and
Nan Jiang and
Satinder Singh and
Ambuj Tewari},
editor = {Firdaus Janoos and
Mehryar Mohri and
Karthik Sridharan},
title = {Markov Decision Processes with Continuous Side Information},
booktitle = {Algorithmic Learning Theory, {ALT} 2018, 7-9 April 2018, Lanzarote,
Canary Islands, Spain},
series = {Proceedings of Machine Learning Research},
volume = {83},
pages = {597--618},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v83/modi18a.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/alt/0002JST18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ZhangDS18a,
author = {Qi Zhang and
Edmund H. Durfee and
Satinder Singh},
editor = {Robin Cohen and
Murat Sensoy and
Timothy J. Norman},
title = {Challenges in the Trustworthy Pursuit of Maintenance Commitments Under
Uncertainty},
booktitle = {Proceedings of the 20th International Trust Workshop co-located with
{AAMAS/IJCAI/ECAI/ICML} 2018, Stockholm, Sweden, July 14, 2018},
series = {{CEUR} Workshop Proceedings},
volume = {2154},
pages = {75--86},
publisher = {CEUR-WS.org},
year = {2018},
url = {https://ceur-ws.org/Vol-2154/paper7.pdf},
timestamp = {Fri, 10 Mar 2023 16:22:57 +0100},
biburl = {https://dblp.org/rec/conf/atal/ZhangDS18a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ZhangDS18,
author = {Shun Zhang and
Edmund H. Durfee and
Satinder Singh},
editor = {Elisabeth Andr{\'{e}} and
Sven Koenig and
Mehdi Dastani and
Gita Sukthankar},
title = {On Querying for Safe Optimality in Factored Markov Decision Processes},
booktitle = {Proceedings of the 17th International Conference on Autonomous Agents
and MultiAgent Systems, {AAMAS} 2018, Stockholm, Sweden, July 10-15,
2018},
pages = {2168--2170},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems
Richland, SC, {USA} / {ACM}},
year = {2018},
url = {http://dl.acm.org/citation.cfm?id=3238108},
timestamp = {Sat, 30 Sep 2023 09:34:53 +0200},
biburl = {https://dblp.org/rec/conf/atal/ZhangDS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/RajendranGSP18,
author = {Janarthanan Rajendran and
Jatin Ganhotra and
Satinder Singh and
Lazaros Polymenakos},
editor = {Ellen Riloff and
David Chiang and
Julia Hockenmaier and
Jun'ichi Tsujii},
title = {Learning End-to-End Goal-Oriented Dialog with Multiple Answers},
booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural
Language Processing, Brussels, Belgium, October 31 - November 4, 2018},
pages = {3834--3843},
publisher = {Association for Computational Linguistics},
year = {2018},
url = {https://doi.org/10.18653/v1/d18-1418},
doi = {10.18653/V1/D18-1418},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/RajendranGSP18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/OhGSL18,
author = {Junhyuk Oh and
Yijie Guo and
Satinder Singh and
Honglak Lee},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Self-Imitation Learning},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {3875--3884},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/oh18b.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/OhGSL18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/ZhangDS18,
author = {Shun Zhang and
Edmund H. Durfee and
Satinder Singh},
editor = {J{\'{e}}r{\^{o}}me Lang},
title = {Minimax-Regret Querying on Side Effects for Safe Optimality in Factored
Markov Decision Processes},
booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on
Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm,
Sweden},
pages = {4867--4873},
publisher = {ijcai.org},
year = {2018},
url = {https://doi.org/10.24963/ijcai.2018/676},
doi = {10.24963/IJCAI.2018/676},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/ZhangDS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/JiangKS18,
author = {Nan Jiang and
Alex Kulesza and
Satinder Singh},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {Completing State Representations using Spectral Learning},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {4333--4342},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/51174add1c52758f33d414ceaf3fe6ba-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/JiangKS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZhengOS18,
author = {Zeyu Zheng and
Junhyuk Oh and
Satinder Singh},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {On Learning Intrinsic Rewards for Policy Gradient Methods},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {4649--4659},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/51de85ddd068f0bc787691d356176df9-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/ZhengOS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-02940,
author = {Jiaxuan Wang and
Ian Fox and
Jonathan Skaza and
Nick Linck and
Satinder Singh and
Jenna Wiens},
title = {The Advantage of Doubling: {A} Deep Reinforcement Learning Approach
to Studying the Double Team in the {NBA}},
journal = {CoRR},
volume = {abs/1803.02940},
year = {2018},
url = {http://arxiv.org/abs/1803.02940},
eprinttype = {arXiv},
eprint = {1803.02940},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-02940.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-06459,
author = {Zeyu Zheng and
Junhyuk Oh and
Satinder Singh},
title = {On Learning Intrinsic Rewards for Policy Gradient Methods},
journal = {CoRR},
volume = {abs/1804.06459},
year = {2018},
url = {http://arxiv.org/abs/1804.06459},
eprinttype = {arXiv},
eprint = {1804.06459},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-06459.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-09540,
author = {Janarthanan Rajendran and
Jatin Ganhotra and
Xiaoxiao Guo and
Mo Yu and
Satinder Singh},
title = {Named Entities troubling your Neural Methods? Build NE-Table: {A}
neural approach for handling Named Entities},
journal = {CoRR},
volume = {abs/1804.09540},
year = {2018},
url = {http://arxiv.org/abs/1804.09540},
eprinttype = {arXiv},
eprint = {1804.09540},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-09540.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-05635,
author = {Junhyuk Oh and
Yijie Guo and
Satinder Singh and
Honglak Lee},
title = {Self-Imitation Learning},
journal = {CoRR},
volume = {abs/1806.05635},
year = {2018},
url = {http://arxiv.org/abs/1806.05635},
eprinttype = {arXiv},
eprint = {1806.05635},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-05635.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-09605,
author = {Vivek Veeriah and
Junhyuk Oh and
Satinder Singh},
title = {Many-Goals Reinforcement Learning},
journal = {CoRR},
volume = {abs/1806.09605},
year = {2018},
url = {http://arxiv.org/abs/1806.09605},
eprinttype = {arXiv},
eprint = {1806.09605},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-09605.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1808-09996,
author = {Janarthanan Rajendran and
Jatin Ganhotra and
Satinder Singh and
Lazaros Polymenakos},
title = {Learning End-to-End Goal-Oriented Dialog with Multiple Answers},
journal = {CoRR},
volume = {abs/1808.09996},
year = {2018},
url = {http://arxiv.org/abs/1808.09996},
eprinttype = {arXiv},
eprint = {1808.09996},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1808-09996.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-00950,
author = {Yijie Guo and
Junhyuk Oh and
Satinder Singh and
Honglak Lee},
title = {Generative Adversarial Self-Imitation Learning},
journal = {CoRR},
volume = {abs/1812.00950},
year = {2018},
url = {http://arxiv.org/abs/1812.00950},
eprinttype = {arXiv},
eprint = {1812.00950},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-00950.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/NguyenWS17,
author = {Thanh Hong Nguyen and
Michael P. Wellman and
Satinder Singh},
title = {A Stackelberg Game Model for Botnet Traffic Exfiltration},
booktitle = {The Workshops of the The Thirty-First {AAAI} Conference on Artificial
Intelligence, Saturday, February 4-9, 2017, San Francisco, California,
{USA}},
series = {{AAAI} Technical Report},
volume = {{WS-17}},
publisher = {{AAAI} Press},
year = {2017},
url = {http://aaai.org/ocs/index.php/WS/AAAIW17/paper/view/15090},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/NguyenWS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/Perez-RosasMRSA17,
author = {Ver{\'{o}}nica P{\'{e}}rez{-}Rosas and
Rada Mihalcea and
Kenneth Resnicow and
Satinder Singh and
Lawrence C. An},
editor = {Regina Barzilay and
Min{-}Yen Kan},
title = {Understanding and Predicting Empathic Behavior in Counseling Therapy},
booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational
Linguistics, {ACL} 2017, Vancouver, Canada, July 30 - August 4, Volume
1: Long Papers},
pages = {1426--1435},
publisher = {Association for Computational Linguistics},
year = {2017},
url = {https://doi.org/10.18653/v1/P17-1131},
doi = {10.18653/V1/P17-1131},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/Perez-RosasMRSA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aips/ZhangDS17,
author = {Shun Zhang and
Edmund H. Durfee and
Satinder Singh},
editor = {Laura Barbulescu and
Jeremy Frank and
Mausam and
Stephen F. Smith},
title = {Approximately-Optimal Queries for Planning in Reward-Uncertain Markov
Decision Processes},
booktitle = {Proceedings of the Twenty-Seventh International Conference on Automated
Planning and Scheduling, {ICAPS} 2017, Pittsburgh, Pennsylvania, USA,
June 18-23, 2017},
pages = {339--347},
publisher = {{AAAI} Press},
year = {2017},
url = {https://aaai.org/ocs/index.php/ICAPS/ICAPS17/paper/view/15763},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aips/ZhangDS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aips/ZhangSD17,
author = {Qi Zhang and
Satinder Singh and
Edmund H. Durfee},
editor = {Laura Barbulescu and
Jeremy Frank and
Mausam and
Stephen F. Smith},
title = {Minimizing Maximum Regret in Commitment Constrained Sequential Decision
Making},
booktitle = {Proceedings of the Twenty-Seventh International Conference on Automated
Planning and Scheduling, {ICAPS} 2017, Pittsburgh, Pennsylvania, USA,
June 18-23, 2017},
pages = {348--357},
publisher = {{AAAI} Press},
year = {2017},
url = {https://aaai.org/ocs/index.php/ICAPS/ICAPS17/paper/view/15766},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aips/ZhangSD17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccs/NguyenWWS17,
author = {Thanh Hong Nguyen and
Mason Wright and
Michael P. Wellman and
Satinder Singh},
editor = {Hamed Okhravi and
Xinming Ou},
title = {Multi-Stage Attack Graph Security Games: Heuristic Strategies, with
Empirical Game-Theoretic Analysis},
booktitle = {Proceedings of the 2017 Workshop on Moving Target Defense, MTD@CCS
2017, Dallas, TX, USA, October 30, 2017},
pages = {87--97},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3140549.3140562},
doi = {10.1145/3140549.3140562},
timestamp = {Thu, 07 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ccs/NguyenWWS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eacl/SinghMPRAGC17,
author = {Ver{\'{o}}nica P{\'{e}}rez{-}Rosas and
Rada Mihalcea and
Kenneth Resnicow and
Satinder Singh and
Lawrence C. An and
Kathy J. Goggin and
Delwyn Catley},
editor = {Mirella Lapata and
Phil Blunsom and
Alexander Koller},
title = {Predicting Counselor Behaviors in Motivational Interviewing Encounters},
booktitle = {Proceedings of the 15th Conference of the European Chapter of the
Association for Computational Linguistics, {EACL} 2017, Valencia,
Spain, April 3-7, 2017, Volume 1: Long Papers},
pages = {1128--1137},
publisher = {Association for Computational Linguistics},
year = {2017},
url = {https://doi.org/10.18653/v1/e17-1106},
doi = {10.18653/V1/E17-1106},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eacl/SinghMPRAGC17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gamesec/NguyenWS17,
author = {Thanh Hong Nguyen and
Michael P. Wellman and
Satinder Singh},
editor = {Stefan Rass and
Bo An and
Christopher Kiekintveld and
Fei Fang and
Stefan Schauer},
title = {A Stackelberg Game Model for Botnet Data Exfiltration},
booktitle = {Decision and Game Theory for Security - 8th International Conference,
GameSec 2017, Vienna, Austria, October 23-25, 2017, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10575},
pages = {151--170},
publisher = {Springer},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-68711-7\_9},
doi = {10.1007/978-3-319-68711-7\_9},
timestamp = {Wed, 07 Feb 2024 17:23:12 +0100},
biburl = {https://dblp.org/rec/conf/gamesec/NguyenWS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/GuoKRBCKTTS17,
author = {Xiaoxiao Guo and
Tim Klinger and
Clemens Rosenbaum and
Joseph P. Bigus and
Murray Campbell and
Ban Kawas and
Kartik Talamadupula and
Gerry Tesauro and
Satinder Singh},
title = {Learning to Query, Reason, and Answer Questions On Ambiguous Texts},
booktitle = {5th International Conference on Learning Representations, {ICLR} 2017,
Toulon, France, April 24-26, 2017, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2017},
url = {https://openreview.net/forum?id=rJ0-tY5xe},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/GuoKRBCKTTS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/OhSLK17,
author = {Junhyuk Oh and
Satinder Singh and
Honglak Lee and
Pushmeet Kohli},
editor = {Doina Precup and
Yee Whye Teh},
title = {Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning},
booktitle = {Proceedings of the 34th International Conference on Machine Learning,
{ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017},
series = {Proceedings of Machine Learning Research},
volume = {70},
pages = {2661--2670},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/oh17a.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/OhSLK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AminJS17,
author = {Kareem Amin and
Nan Jiang and
Satinder Singh},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Repeated Inverse Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {1815--1824},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/8ce6790cc6a94e65f17f908f462fae85-Abstract.html},
timestamp = {Mon, 22 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/AminJS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/OhSL17,
author = {Junhyuk Oh and
Satinder Singh and
Honglak Lee},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Value Prediction Network},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {6118--6128},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/ffbd6cbb019a1413183c8d08f2929307-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/OhSL17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/aaai/2017,
editor = {Satinder Singh and
Shaul Markovitch},
title = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence,
February 4-9, 2017, San Francisco, California, {USA}},
publisher = {{AAAI} Press},
year = {2017},
url = {https://ojs.aaai.org/index.php/AAAI/issue/view/302},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/2017.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhangSD17,
author = {Qi Zhang and
Satinder Singh and
Edmund H. Durfee},
title = {Minimizing Maximum Regret in Commitment Constrained Sequential Decision
Making},
journal = {CoRR},
volume = {abs/1703.04587},
year = {2017},
url = {http://arxiv.org/abs/1703.04587},
eprinttype = {arXiv},
eprint = {1703.04587},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhangSD17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AminJS17,
author = {Kareem Amin and
Nan Jiang and
Satinder Singh},
title = {Repeated Inverse Reinforcement Learning},
journal = {CoRR},
volume = {abs/1705.05427},
year = {2017},
url = {http://arxiv.org/abs/1705.05427},
eprinttype = {arXiv},
eprint = {1705.05427},
timestamp = {Mon, 22 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AminJS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/OhSLK17,
author = {Junhyuk Oh and
Satinder Singh and
Honglak Lee and
Pushmeet Kohli},
title = {Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1706.05064},
year = {2017},
url = {http://arxiv.org/abs/1706.05064},
eprinttype = {arXiv},
eprint = {1706.05064},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/OhSLK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/OhSL17,
author = {Junhyuk Oh and
Satinder Singh and
Honglak Lee},
title = {Value Prediction Network},
journal = {CoRR},
volume = {abs/1707.03497},
year = {2017},
url = {http://arxiv.org/abs/1707.03497},
eprinttype = {arXiv},
eprint = {1707.03497},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/OhSL17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-05726,
author = {Aditya Modi and
Nan Jiang and
Satinder Singh and
Ambuj Tewari},
title = {Markov Decision Processes with Continuous Side Information},
journal = {CoRR},
volume = {abs/1711.05726},
year = {2017},
url = {http://arxiv.org/abs/1711.05726},
eprinttype = {arXiv},
eprint = {1711.05726},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-05726.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/EsbroeckSSSK16,
author = {Alexander Van Esbroeck and
Landon Smith and
Zeeshan Syed and
Satinder Singh and
Zahi N. Karam},
title = {Multi-task seizure detection: addressing intra-patient variation in
seizure morphologies},
journal = {Mach. Learn.},
volume = {102},
number = {3},
pages = {309--321},
year = {2016},
url = {https://doi.org/10.1007/s10994-015-5519-7},
doi = {10.1007/S10994-015-5519-7},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/EsbroeckSSSK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/JiangKS16,
author = {Nan Jiang and
Alex Kulesza and
Satinder Singh},
editor = {Dale Schuurmans and
Michael P. Wellman},
title = {Improving Predictive State Representations via Gradient Descent},
booktitle = {Proceedings of the Thirtieth {AAAI} Conference on Artificial Intelligence,
February 12-17, 2016, Phoenix, Arizona, {USA}},
pages = {1709--1715},
publisher = {{AAAI} Press},
year = {2016},
url = {https://doi.org/10.1609/aaai.v30i1.10270},
doi = {10.1609/AAAI.V30I1.10270},
timestamp = {Mon, 04 Sep 2023 15:08:28 +0200},
biburl = {https://dblp.org/rec/conf/aaai/JiangKS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/DurfeeS16a,
author = {Edmund H. Durfee and
Satinder Singh},
editor = {Nardine Osman and
Carles Sierra},
title = {On the Trustworthy Fulfillment of Commitments},
booktitle = {Autonomous Agents and Multiagent Systems - {AAMAS} 2016 Workshops,
- Best Papers - , Singapore, Singapore, May 9-10, 2016, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {10002},
pages = {1--13},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-46882-2\_1},
doi = {10.1007/978-3-319-46882-2\_1},
timestamp = {Thu, 08 Sep 2022 19:48:31 +0200},
biburl = {https://dblp.org/rec/conf/atal/DurfeeS16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/DurfeeS16,
author = {Edmund H. Durfee and
Satinder Singh},
editor = {Jie Zhang and
Robin Cohen and
Murat Sensoy},
title = {On the Trustworthy Fulfillment of Commitments},
booktitle = {Proceedings of the 18th International Workshop on Trust in Agent Societies
co-located with the 15th International Conference on Autonomous Agents
and Multiagent Systems {(AAMAS} 2016), Singapore, Singapore, May 10,
2016},
series = {{CEUR} Workshop Proceedings},
volume = {1578},
pages = {54--62},
publisher = {CEUR-WS.org},
year = {2016},
url = {https://ceur-ws.org/Vol-1578/paper9.pdf},
timestamp = {Fri, 10 Mar 2023 16:22:57 +0100},
biburl = {https://dblp.org/rec/conf/atal/DurfeeS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/OhCSL16,
author = {Junhyuk Oh and
Valliappa Chockalingam and
Satinder Singh and
Honglak Lee},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Control of Memory, Active Perception, and Action in Minecraft},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {2790--2799},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/oh16.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/OhCSL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/GuoSLL16,
author = {Xiaoxiao Guo and
Satinder Singh and
Richard L. Lewis and
Honglak Lee},
editor = {Subbarao Kambhampati},
title = {Deep Learning for Reward Design to Improve Monte Carlo Tree Search
in {ATARI} Games},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI} 2016, New York, NY, USA, 9-15 July
2016},
pages = {1519--1525},
publisher = {{IJCAI/AAAI} Press},
year = {2016},
url = {http://www.ijcai.org/Abstract/16/218},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/GuoSLL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/JiangST16,
author = {Nan Jiang and
Satinder Singh and
Ambuj Tewari},
editor = {Subbarao Kambhampati},
title = {On Structural Properties of MDPs that Bound Loss Due to Shallow Planning},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI} 2016, New York, NY, USA, 9-15 July
2016},
pages = {1640--1647},
publisher = {{IJCAI/AAAI} Press},
year = {2016},
url = {http://www.ijcai.org/Abstract/16/235},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/JiangST16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/ZhangDSCW16,
author = {Qi Zhang and
Edmund H. Durfee and
Satinder Singh and
Anna Chen and
Stefan J. Witwicki},
editor = {Subbarao Kambhampati},
title = {Commitment Semantics for Sequential Decision Making under Reward Uncertainty},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI} 2016, New York, NY, USA, 9-15 July
2016},
pages = {3315--3323},
publisher = {{IJCAI/AAAI} Press},
year = {2016},
url = {http://www.ijcai.org/Abstract/16/469},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/ZhangDSCW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/JiangKSL16,
author = {Nan Jiang and
Alex Kulesza and
Satinder Singh and
Richard L. Lewis},
editor = {Subbarao Kambhampati},
title = {The Dependence of Effective Planning Horizon on Model Accuracy},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI} 2016, New York, NY, USA, 9-15 July
2016},
pages = {4180--4189},
publisher = {{IJCAI/AAAI} Press},
year = {2016},
url = {http://www.ijcai.org/Abstract/16/626},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/JiangKSL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/Perez-RosasMRSA16,
author = {Ver{\'{o}}nica P{\'{e}}rez{-}Rosas and
Rada Mihalcea and
Kenneth Resnicow and
Satinder Singh and
Lawrence C. An},
editor = {Kristy Hollingshead and
Lyle H. Ungar},
title = {Building a Motivational Interviewing Dataset},
booktitle = {Proceedings of the 3rd Workshop on Computational Linguistics and Clinical
Psychology: From Linguistic Signal to Clinical Reality, CLPsych@NAACL-HLT
2016, June 16, 2016, San Diego, California, {USA}},
pages = {42--51},
publisher = {The Association for Computational Linguistics},
year = {2016},
url = {https://doi.org/10.18653/v1/w16-0305},
doi = {10.18653/V1/W16-0305},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/naacl/Perez-RosasMRSA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/AminWS16,
author = {Kareem Amin and
Michael P. Wellman and
Satinder Singh},
editor = {Alexander Ihler and
Dominik Janzing},
title = {Gradient Methods for Stackelberg Games},
booktitle = {Proceedings of the Thirty-Second Conference on Uncertainty in Artificial
Intelligence, {UAI} 2016, June 25-29, 2016, New York City, NY, {USA}},
publisher = {{AUAI} Press},
year = {2016},
url = {http://auai.org/uai2016/proceedings/papers/167.pdf},
timestamp = {Mon, 05 Dec 2022 15:54:38 +0100},
biburl = {https://dblp.org/rec/conf/uai/AminWS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AminS16,
author = {Kareem Amin and
Satinder Singh},
title = {Towards Resolving Unidentifiability in Inverse Reinforcement Learning},
journal = {CoRR},
volume = {abs/1601.06569},
year = {2016},
url = {http://arxiv.org/abs/1601.06569},
eprinttype = {arXiv},
eprint = {1601.06569},
timestamp = {Mon, 22 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AminS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/GuoSLL16,
author = {Xiaoxiao Guo and
Satinder Singh and
Richard L. Lewis and
Honglak Lee},
title = {Deep Learning for Reward Design to Improve Monte Carlo Tree Search
in {ATARI} Games},
journal = {CoRR},
volume = {abs/1604.07095},
year = {2016},
url = {http://arxiv.org/abs/1604.07095},
eprinttype = {arXiv},
eprint = {1604.07095},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/GuoSLL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/OhCSL16,
author = {Junhyuk Oh and
Valliappa Chockalingam and
Satinder Singh and
Honglak Lee},
title = {Control of Memory, Active Perception, and Action in Minecraft},
journal = {CoRR},
volume = {abs/1605.09128},
year = {2016},
url = {http://arxiv.org/abs/1605.09128},
eprinttype = {arXiv},
eprint = {1605.09128},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/OhCSL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/KuleszaJS15,
author = {Alex Kulesza and
Nan Jiang and
Satinder Singh},
editor = {Blai Bonet and
Sven Koenig},
title = {Spectral Learning of Predictive State Representations with Insufficient
Statistics},
booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence,
January 25-30, 2015, Austin, Texas, {USA}},
pages = {2715--2721},
publisher = {{AAAI} Press},
year = {2015},
url = {https://doi.org/10.1609/aaai.v29i1.9635},
doi = {10.1609/AAAI.V29I1.9635},
timestamp = {Mon, 18 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/KuleszaJS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaifs/DurfeeS15,
author = {Edmund H. Durfee and
Satinder Singh},
title = {Commitment Semantics for Sequential Decision Making Under Reward Uncertainty},
booktitle = {2015 {AAAI} Fall Symposia, Arlington, Virginia, USA, November 12-14,
2015},
pages = {13--20},
publisher = {{AAAI} Press},
year = {2015},
url = {http://www.aaai.org/ocs/index.php/FSS/FSS15/paper/view/11652},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaaifs/DurfeeS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/KuleszaJS15,
author = {Alex Kulesza and
Nan Jiang and
Satinder Singh},
editor = {Guy Lebanon and
S. V. N. Vishwanathan},
title = {Low-Rank Spectral Learning with Weighted Loss Functions},
booktitle = {Proceedings of the Eighteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2015, San Diego, California,
USA, May 9-12, 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {38},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v38/kulesza15.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/KuleszaJS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/JiangKSL15,
author = {Nan Jiang and
Alex Kulesza and
Satinder Singh and
Richard L. Lewis},
editor = {Gerhard Weiss and
Pinar Yolum and
Rafael H. Bordini and
Edith Elkind},
title = {The Dependence of Effective Planning Horizon on Model Accuracy},
booktitle = {Proceedings of the 2015 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2015, Istanbul, Turkey, May 4-8, 2015},
pages = {1181--1189},
publisher = {{ACM}},
year = {2015},
url = {http://dl.acm.org/citation.cfm?id=2773300},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/JiangKSL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/JiangKS15,
author = {Nan Jiang and
Alex Kulesza and
Satinder Singh},
editor = {Francis R. Bach and
David M. Blei},
title = {Abstraction Selection in Model-based Reinforcement Learning},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {179--188},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/jiang15.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/JiangKS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/OhGLLS15,
author = {Junhyuk Oh and
Xiaoxiao Guo and
Honglak Lee and
Richard L. Lewis and
Satinder Singh},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Action-Conditional Video Prediction using Deep Networks in Atari Games},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {2863--2871},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/6ba3af5d7b2790e73f0de32e5c8c1798-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/OhGLLS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/OhGLLS15,
author = {Junhyuk Oh and
Xiaoxiao Guo and
Honglak Lee and
Richard L. Lewis and
Satinder Singh},
title = {Action-Conditional Video Prediction using Deep Networks in Atari Games},
journal = {CoRR},
volume = {abs/1507.08750},
year = {2015},
url = {http://arxiv.org/abs/1507.08750},
eprinttype = {arXiv},
eprint = {1507.08750},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/OhGLLS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tamd/LiuSLQ14,
author = {Bingyao Liu and
Satinder Singh and
Richard L. Lewis and
Shiyin Qin},
title = {Optimal Rewards for Cooperative Agents},
journal = {{IEEE} Trans. Auton. Ment. Dev.},
volume = {6},
number = {4},
pages = {286--297},
year = {2014},
url = {https://doi.org/10.1109/TAMD.2014.2362682},
doi = {10.1109/TAMD.2014.2362682},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tamd/LiuSLQ14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/topics/HowesLS14,
author = {Andrew Howes and
Richard L. Lewis and
Satinder Singh},
title = {Utility Maximization and Bounds on Human Information Processing},
journal = {Top. Cogn. Sci.},
volume = {6},
number = {2},
pages = {198--203},
year = {2014},
url = {https://doi.org/10.1111/tops.12089},
doi = {10.1111/TOPS.12089},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/topics/HowesLS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/topics/LewisHS14,
author = {Richard L. Lewis and
Andrew Howes and
Satinder Singh},
title = {Computational Rationality: Linking Mechanism and Behavior Through
Bounded Utility Maximization},
journal = {Top. Cogn. Sci.},
volume = {6},
number = {2},
pages = {279--311},
year = {2014},
url = {https://doi.org/10.1111/tops.12086},
doi = {10.1111/TOPS.12086},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/topics/LewisHS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ChiaBKSS14,
author = {Chih{-}Chun Chia and
James Blum and
Zahi N. Karam and
Satinder Singh and
Zeeshan Syed},
editor = {Carla E. Brodley and
Peter Stone},
title = {Predicting Postoperative Atrial Fibrillation from Independent {ECG}
Components},
booktitle = {Proceedings of the Twenty-Eighth {AAAI} Conference on Artificial Intelligence,
July 27 -31, 2014, Qu{\'{e}}bec City, Qu{\'{e}}bec, Canada},
pages = {1178--1184},
publisher = {{AAAI} Press},
year = {2014},
url = {https://doi.org/10.1609/aaai.v28i1.8921},
doi = {10.1609/AAAI.V28I1.8921},
timestamp = {Mon, 04 Sep 2023 15:06:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ChiaBKSS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/EsbroeckSRS14,
author = {Alexander Van Esbroeck and
Satinder Singh and
Ilan Rubinfeld and
Zeeshan Syed},
editor = {Carla E. Brodley and
Peter Stone},
title = {Evaluating Trauma Patients: Addressing Missing Covariates with Joint
Optimization},
booktitle = {Proceedings of the Twenty-Eighth {AAAI} Conference on Artificial Intelligence,
July 27 -31, 2014, Qu{\'{e}}bec City, Qu{\'{e}}bec, Canada},
pages = {1307--1313},
publisher = {{AAAI} Press},
year = {2014},
url = {https://doi.org/10.1609/aaai.v28i1.8912},
doi = {10.1609/AAAI.V28I1.8912},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/EsbroeckSRS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl-cmcl/ShvartsmanLS14,
author = {Michael Shvartsman and
Richard L. Lewis and
Satinder Singh},
editor = {Vera Demberg and
Timothy O'Donnell},
title = {Computationally Rational Saccadic Control: An Explanation of Spillover
Effects Based on Sampling from Noisy Perception and Memory},
booktitle = {Proceedings of the Fifth Workshop on Cognitive Modeling and Computational
Linguistics, CMCL@ACL 2014, Baltimore, Maryland, USA, June 26, 2014},
pages = {1--9},
publisher = {Association for Computational Linguistics},
year = {2014},
url = {https://doi.org/10.3115/v1/W14-2001},
doi = {10.3115/V1/W14-2001},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl-cmcl/ShvartsmanLS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aips/VorobeychikATS14,
author = {Yevgeniy Vorobeychik and
Bo An and
Milind Tambe and
Satinder Singh},
editor = {Steve A. Chien and
Minh Binh Do and
Alan Fern and
Wheeler Ruml},
title = {Computing Solutions in Infinite-Horizon Discounted Adversarial Patrolling
Games},
booktitle = {Proceedings of the Twenty-Fourth International Conference on Automated
Planning and Scheduling, {ICAPS} 2014, Portsmouth, New Hampshire,
USA, June 21-26, 2014},
publisher = {{AAAI}},
year = {2014},
url = {http://www.aaai.org/ocs/index.php/ICAPS/ICAPS14/paper/view/7783},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aips/VorobeychikATS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/CohnSD14,
author = {Robert Cohn and
Satinder Singh and
Edmund H. Durfee},
title = {Characterizing EVOI-Sufficient k-Response Query Sets in Decision Problems},
booktitle = {Proceedings of the Seventeenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2014, Reykjavik, Iceland, April
22-25, 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {33},
pages = {131--139},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v33/cohn14.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/CohnSD14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/KuleszaRS14,
author = {Alex Kulesza and
N. Raj Rao and
Satinder Singh},
title = {Low-Rank Spectral Learning},
booktitle = {Proceedings of the Seventeenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2014, Reykjavik, Iceland, April
22-25, 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {33},
pages = {522--530},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v33/kulesza14.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/KuleszaRS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/JiangSL14,
author = {Nan Jiang and
Satinder Singh and
Richard L. Lewis},
editor = {Ana L. C. Bazzan and
Michael N. Huhns and
Alessio Lomuscio and
Paul Scerri},
title = {Improving {UCT} planning via approximate homomorphisms},
booktitle = {International conference on Autonomous Agents and Multi-Agent Systems,
{AAMAS} '14, Paris, France, May 5-9, 2014},
pages = {1289--1296},
publisher = {{IFAAMAS/ACM}},
year = {2014},
url = {http://dl.acm.org/citation.cfm?id=2617453},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/JiangSL14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KaramPSMAHM14,
author = {Zahi N. Karam and
Emily Mower Provost and
Satinder Singh and
Jennifer Montgomery and
Christopher Archer and
Gloria Harrington and
Melvin G. McInnis},
title = {Ecologically valid long-term mood monitoring of individuals with bipolar
disorder using speech},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {4858--4862},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6854525},
doi = {10.1109/ICASSP.2014.6854525},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KaramPSMAHM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GuoSLLW14,
author = {Xiaoxiao Guo and
Satinder Singh and
Honglak Lee and
Richard L. Lewis and
Xiaoshi Wang},
editor = {Zoubin Ghahramani and
Max Welling and
Corinna Cortes and
Neil D. Lawrence and
Kilian Q. Weinberger},
title = {Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo
Tree Search Planning},
booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference
on Neural Information Processing Systems 2014, December 8-13 2014,
Montreal, Quebec, Canada},
pages = {3338--3346},
year = {2014},
url = {https://proceedings.neurips.cc/paper/2014/hash/8bb88f80d334b1869781beb89f7b73be-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/GuoSLLW14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TalvitieS14,
author = {Erik Talvitie and
Satinder Singh},
title = {Learning to Make Predictions In Partially Observable Environments
Without a Generative Model},
journal = {CoRR},
volume = {abs/1401.3870},
year = {2014},
url = {http://arxiv.org/abs/1401.3870},
eprinttype = {arXiv},
eprint = {1401.3870},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TalvitieS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/topics/LewisSS13,
author = {Richard L. Lewis and
Michael Shvartsman and
Satinder Singh},
title = {The Adaptive Nature of Eye Movements in Linguistic Tasks: How Payoff
and Architecture Shape Speed-Accuracy Trade-Offs},
journal = {Top. Cogn. Sci.},
volume = {5},
number = {3},
pages = {581--610},
year = {2013},
url = {https://doi.org/10.1111/tops.12032},
doi = {10.1111/TOPS.12032},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/topics/LewisSS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hci/FearyBCHLSS13,
author = {Michael Feary and
Dorrit Billman and
Xiuli Chen and
Andrew Howes and
Richard L. Lewis and
Lance Sherry and
Satinder Singh},
editor = {Masaaki Kurosu},
title = {Linking Context to Evaluation in the Design of Safety Critical Interfaces},
booktitle = {Human-Computer Interaction. Human-Centred Design Approaches, Methods,
Tools, and Environments - 15th International Conference, {HCI} International
2013, Las Vegas, NV, USA, July 21-26, 2013, Proceedings, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {8004},
pages = {193--202},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-642-39232-0\_22},
doi = {10.1007/978-3-642-39232-0\_22},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/hci/FearyBCHLSS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GuoSL13,
author = {Xiaoxiao Guo and
Satinder Singh and
Richard L. Lewis},
editor = {Christopher J. C. Burges and
L{\'{e}}on Bottou and
Zoubin Ghahramani and
Kilian Q. Weinberger},
title = {Reward Mapping for Transfer in Long-Lived Agents},
booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual
Conference on Neural Information Processing Systems 2013. Proceedings
of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States},
pages = {2130--2138},
year = {2013},
url = {https://proceedings.neurips.cc/paper/2013/hash/58c54802a9fb9526cd0923353a34a7ae-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/GuoSL13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1301-2281,
author = {Michael J. Kearns and
Michael L. Littman and
Satinder Singh},
title = {Graphical Models for Game Theory},
journal = {CoRR},
volume = {abs/1301.2281},
year = {2013},
url = {http://arxiv.org/abs/1301.2281},
eprinttype = {arXiv},
eprint = {1301.2281},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1301-2281.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1301-3867,
author = {Michael J. Kearns and
Yishay Mansour and
Satinder Singh},
title = {Fast Planning in Stochastic Games},
journal = {CoRR},
volume = {abs/1301.3867},
year = {2013},
url = {http://arxiv.org/abs/1301.3867},
eprinttype = {arXiv},
eprint = {1301.3867},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1301-3867.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1301-3892,
author = {Satinder Singh and
Michael J. Kearns and
Yishay Mansour},
title = {Nash Convergence of Gradient Dynamics in Iterated General-Sum Games},
journal = {CoRR},
volume = {abs/1301.3892},
year = {2013},
url = {http://arxiv.org/abs/1301.3892},
eprinttype = {arXiv},
eprint = {1301.3892},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1301-3892.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1301-6718,
author = {Yishay Mansour and
Satinder Singh},
title = {On the Complexity of Policy Iteration},
journal = {CoRR},
volume = {abs/1301.6718},
year = {2013},
url = {http://arxiv.org/abs/1301.6718},
eprinttype = {arXiv},
eprint = {1301.6718},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1301-6718.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1301-6719,
author = {David A. McAllester and
Satinder Singh},
title = {Approximate Planning for Factored POMDPs using Belief State Simplification},
journal = {CoRR},
volume = {abs/1301.6719},
year = {2013},
url = {http://arxiv.org/abs/1301.6719},
eprinttype = {arXiv},
eprint = {1301.6719},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1301-6719.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aim/AgmonAAABDGGGJKKLLMMMOOOPPRRTSSSSSSUW12,
author = {Noa Agmon and
Vikas Agrawal and
David W. Aha and
Yiannis Aloimonos and
Donagh Buckley and
Prashant Doshi and
Christopher W. Geib and
Floriana Grasso and
Nancy L. Green and
Benjamin Johnston and
Burt Kaliski and
Christopher Kiekintveld and
Edith Law and
Henry Lieberman and
Ole J. Mengshoel and
Ted Metzler and
Joseph Modayil and
Douglas W. Oard and
Nilufer Onder and
Barry O'Sullivan and
Katerina Pastra and
Doina Precup and
Sowmya Ramachandran and
Chris Reed and
Sanem Sariel Talay and
Ted Selker and
Lokendra Shastri and
Stephen F. Smith and
Satinder Singh and
Siddharth Srivastava and
Gita Sukthankar and
David C. Uthus and
Mary{-}Anne Williams},
title = {Reports of the {AAAI} 2011 Conference Workshops},
journal = {{AI} Mag.},
volume = {33},
number = {1},
pages = {57--70},
year = {2012},
url = {https://doi.org/10.1609/aimag.v33i1.2390},
doi = {10.1609/AIMAG.V33I1.2390},
timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aim/AgmonAAABDGGGJKKLLMMMOOOPPRRTSSSSSSUW12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/AnKKSSTV12,
author = {Bo An and
David Kempe and
Christopher Kiekintveld and
Eric Shieh and
Satinder Singh and
Milind Tambe and
Yevgeniy Vorobeychik},
editor = {J{\"{o}}rg Hoffmann and
Bart Selman},
title = {Security Games with Limited Surveillance},
booktitle = {Proceedings of the Twenty-Sixth {AAAI} Conference on Artificial Intelligence,
July 22-26, 2012, Toronto, Ontario, Canada},
pages = {1241--1248},
publisher = {{AAAI} Press},
year = {2012},
url = {https://doi.org/10.1609/aaai.v26i1.8236},
doi = {10.1609/AAAI.V26I1.8236},
timestamp = {Mon, 04 Sep 2023 15:56:47 +0200},
biburl = {https://dblp.org/rec/conf/aaai/AnKKSSTV12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/VorobeychikS12,
author = {Yevgeniy Vorobeychik and
Satinder Singh},
editor = {J{\"{o}}rg Hoffmann and
Bart Selman},
title = {Computing Stackelberg Equilibria in Discounted Stochastic Games},
booktitle = {Proceedings of the Twenty-Sixth {AAAI} Conference on Artificial Intelligence,
July 22-26, 2012, Toronto, Ontario, Canada},
pages = {1478--1484},
publisher = {{AAAI} Press},
year = {2012},
url = {https://doi.org/10.1609/aaai.v26i1.8234},
doi = {10.1609/AAAI.V26I1.8234},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/VorobeychikS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaiss/AnKKSSTV12,
author = {Bo An and
David Kempe and
Christopher Kiekintveld and
Eric Anyung Shieh and
Satinder Singh and
Milind Tambe and
Yevgeniy Vorobeychik},
title = {Security Games with Limited Surveillance: An Initial Report},
booktitle = {Game Theory for Security, Sustainability, and Health, Papers from
the 2012 {AAAI} Spring Symposium, Palo Alto, California, USA, March
26-28, 2012},
series = {{AAAI} Technical Report},
volume = {{SS-12-03}},
publisher = {{AAAI}},
year = {2012},
url = {http://www.aaai.org/ocs/index.php/SSS/SSS12/paper/view/4262},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaaiss/AnKKSSTV12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aamas/BratmanSSL12,
author = {Jeshua Bratman and
Satinder Singh and
Jonathan Sorg and
Richard L. Lewis},
editor = {Wiebe van der Hoek and
Lin Padgham and
Vincent Conitzer and
Michael Winikoff},
title = {Strong mitigation: nesting search for good policies within search
for good reward},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems,
{AAMAS} 2012, Valencia, Spain, June 4-8, 2012 {(3} Volumes)},
pages = {407--414},
publisher = {{IFAAMAS}},
year = {2012},
url = {http://dl.acm.org/citation.cfm?id=2343634},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aamas/BratmanSSL12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aamas/DuongWSK12,
author = {Quang Duong and
Michael P. Wellman and
Satinder Singh and
Michael J. Kearns},
editor = {Wiebe van der Hoek and
Lin Padgham and
Vincent Conitzer and
Michael Winikoff},
title = {Learning and predicting dynamic networked behavior with graphical
multiagent models},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems,
{AAMAS} 2012, Valencia, Spain, June 4-8, 2012 {(3} Volumes)},
pages = {441--448},
publisher = {{IFAAMAS}},
year = {2012},
url = {http://dl.acm.org/citation.cfm?id=2343639},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aamas/DuongWSK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aamas/WitwickiCDS12,
author = {Stefan J. Witwicki and
Inn{-}Tung Chen and
Edmund H. Durfee and
Satinder Singh},
editor = {Wiebe van der Hoek and
Lin Padgham and
Vincent Conitzer and
Michael Winikoff},
title = {Planning and evaluating multiagent influences under reward uncertainty},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems,
{AAMAS} 2012, Valencia, Spain, June 4-8, 2012 {(3} Volumes)},
pages = {1277--1278},
publisher = {{IFAAMAS}},
year = {2012},
url = {http://dl.acm.org/citation.cfm?id=2343961},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aamas/WitwickiCDS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdl-epirob/LiuSLQ12,
author = {Bingyao Liu and
Satinder Singh and
Richard L. Lewis and
Shiyin Qin},
title = {Optimal rewards in multiagent teams},
booktitle = {2012 {IEEE} International Conference on Development and Learning and
Epigenetic Robotics, {ICDL-EPIROB} 2012, San Diego, CA, USA, November
7-9, 2012},
pages = {1--8},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/DevLrn.2012.6400862},
doi = {10.1109/DEVLRN.2012.6400862},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icdl-epirob/LiuSLQ12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigecom/SandholmS12,
author = {Tuomas Sandholm and
Satinder Singh},
editor = {Boi Faltings and
Kevin Leyton{-}Brown and
Panos Ipeirotis},
title = {Lossy stochastic game abstraction with bounds},
booktitle = {Proceedings of the 13th {ACM} Conference on Electronic Commerce, {EC}
2012, Valencia, Spain, June 4-8, 2012},
pages = {880--897},
publisher = {{ACM}},
year = {2012},
url = {https://doi.org/10.1145/2229012.2229079},
doi = {10.1145/2229012.2229079},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sigecom/SandholmS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1203-3518,
author = {Jonathan Sorg and
Satinder Singh and
Richard L. Lewis},
title = {Variance-Based Rewards for Approximate Bayesian Reinforcement Learning},
journal = {CoRR},
volume = {abs/1203.3518},
year = {2012},
url = {http://arxiv.org/abs/1203.3518},
eprinttype = {arXiv},
eprint = {1203.3518},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1203-3518.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1206-3248,
author = {Quang Duong and
Michael P. Wellman and
Satinder Singh},
title = {Knowledge Combination in Graphical Multiagent Model},
journal = {CoRR},
volume = {abs/1206.3248},
year = {2012},
url = {http://arxiv.org/abs/1206.3248},
eprinttype = {arXiv},
eprint = {1206.3248},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1206-3248.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/CavalloPS12,
author = {Ruggiero Cavallo and
David C. Parkes and
Satinder Singh},
title = {Optimal Coordinated Planning Amongst Self-Interested Agents with Private
State},
journal = {CoRR},
volume = {abs/1206.6820},
year = {2012},
url = {http://arxiv.org/abs/1206.6820},
eprinttype = {arXiv},
eprint = {1206.6820},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/CavalloPS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1207-1416,
author = {Matthew R. Rudary and
Satinder Singh and
David Wingate},
title = {Predictive Linear-Gaussian Models of Stochastic Dynamical Systems},
journal = {CoRR},
volume = {abs/1207.1416},
year = {2012},
url = {http://arxiv.org/abs/1207.1416},
eprinttype = {arXiv},
eprint = {1207.1416},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1207-1416.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1207-4167,
author = {Satinder Singh and
Michael R. James and
Matthew R. Rudary},
title = {Predictive State Representations: {A} New Theory for Modeling Dynamical
Systems},
journal = {CoRR},
volume = {abs/1207.4167},
year = {2012},
url = {http://arxiv.org/abs/1207.4167},
eprinttype = {arXiv},
eprint = {1207.4167},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1207-4167.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/basesearch/Singh11,
author = {Satinder Pal Singh},
title = {{IP} Geolocation in Metropolitan Areas},
school = {University of Maryland, College Park, MD, {USA}},
year = {2011},
url = {https://hdl.handle.net/1903/11505},
timestamp = {Wed, 04 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/basesearch/Singh11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/TalvitieS11,
author = {Erik Talvitie and
Satinder Singh},
title = {Learning to Make Predictions In Partially Observable Environments
Without a Generative Model},
journal = {J. Artif. Intell. Res.},
volume = {42},
pages = {353--392},
year = {2011},
url = {https://doi.org/10.1613/jair.3396},
doi = {10.1613/JAIR.3396},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jair/TalvitieS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SorgSL11,
author = {Jonathan Sorg and
Satinder Singh and
Richard L. Lewis},
editor = {Wolfram Burgard and
Dan Roth},
title = {Optimal Rewards versus Leaf-Evaluation Heuristics in Planning Agents},
booktitle = {Proceedings of the Twenty-Fifth {AAAI} Conference on Artificial Intelligence,
{AAAI} 2011, San Francisco, California, USA, August 7-11, 2011},
pages = {465--470},
publisher = {{AAAI} Press},
year = {2011},
url = {https://doi.org/10.1609/aaai.v25i1.7931},
doi = {10.1609/AAAI.V25I1.7931},
timestamp = {Mon, 04 Sep 2023 16:05:54 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SorgSL11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/CohnDS11,
author = {Robert Cohn and
Edmund H. Durfee and
Satinder Singh},
editor = {Wolfram Burgard and
Dan Roth},
title = {Comparing Action-Query Strategies in Semi-Autonomous Agents},
booktitle = {Proceedings of the Twenty-Fifth {AAAI} Conference on Artificial Intelligence,
{AAAI} 2011, San Francisco, California, USA, August 7-11, 2011},
pages = {1102--1107},
publisher = {{AAAI} Press},
year = {2011},
url = {https://doi.org/10.1609/aaai.v25i1.7992},
doi = {10.1609/AAAI.V25I1.7992},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/CohnDS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/CohnDS11,
author = {Robert Cohn and
Edmund H. Durfee and
Satinder Singh},
editor = {Liz Sonenberg and
Peter Stone and
Kagan Tumer and
Pinar Yolum},
title = {Comparing action-query strategies in semi-autonomous agents},
booktitle = {10th International Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2011), Taipei, Taiwan, May 2-6, 2011, Volume 1-3},
pages = {1287--1288},
publisher = {{IFAAMAS}},
year = {2011},
url = {http://portal.acm.org/citation.cfm?id=2034529\&\#38;CFID=69154334\&\#38;CFTOKEN=45298625},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/CohnDS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigmetrics/SinghBLBLS11,
author = {Satinder Pal Singh and
Randolph Baden and
Choon Lee and
Bobby Bhattacharjee and
Richard J. La and
Mark A. Shayman},
editor = {Arif Merchant and
Kimberly Keeton and
Dan Rubenstein},
title = {{IP} geolocation in metropolitan areas},
booktitle = {{SIGMETRICS} 2011, Proceedings of the 2011 {ACM} {SIGMETRICS} International
Conference on Measurement and Modeling of Computer Systems, San Jose,
CA, USA, 07-11 June 2011 (Co-located with {FCRC} 2011)},
pages = {155--156},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/1993744.1993803},
doi = {10.1145/1993744.1993803},
timestamp = {Sun, 01 Aug 2021 14:20:40 +0200},
biburl = {https://dblp.org/rec/conf/sigmetrics/SinghBLBLS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/socialcom/DuongWS11,
author = {Quang Duong and
Michael P. Wellman and
Satinder Singh},
title = {Modeling Information Diffusion in Networks with Unobserved Links},
booktitle = {PASSAT/SocialCom 2011, Privacy, Security, Risk and Trust (PASSAT),
2011 {IEEE} Third International Conference on and 2011 {IEEE} Third
International Conference on Social Computing (SocialCom), Boston,
MA, USA, 9-11 Oct., 2011},
pages = {362--369},
publisher = {{IEEE} Computer Society},
year = {2011},
url = {https://doi.org/10.1109/PASSAT/SocialCom.2011.50},
doi = {10.1109/PASSAT/SOCIALCOM.2011.50},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/socialcom/DuongWS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1106-0676,
author = {Michael J. Kearns and
Diane J. Litman and
Satinder Singh and
Marilyn A. Walker},
title = {Optimizing Dialogue Management with Reinforcement Learning: Experiments
with the NJFun System},
journal = {CoRR},
volume = {abs/1106.0676},
year = {2011},
url = {http://arxiv.org/abs/1106.0676},
eprinttype = {arXiv},
eprint = {1106.0676},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1106-0676.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1106-0678,
author = {Michael J. Kearns and
Michael L. Littman and
Satinder Singh and
Peter Stone},
title = {ATTac-2000: An Adaptive Autonomous Bidding Agent},
journal = {CoRR},
volume = {abs/1106.0678},
year = {2011},
url = {http://arxiv.org/abs/1106.0678},
eprinttype = {arXiv},
eprint = {1106.0678},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1106-0678.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aim/ParkesCCS10,
author = {David C. Parkes and
Ruggiero Cavallo and
Florin Constantin and
Satinder Singh},
title = {Dynamic Incentive Mechanisms},
journal = {{AI} Mag.},
volume = {31},
number = {4},
pages = {79--94},
year = {2010},
url = {https://doi.org/10.1609/aimag.v31i4.2316},
doi = {10.1609/AIMAG.V31I4.2316},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aim/ParkesCCS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tamd/SinghLBS10,
author = {Satinder Singh and
Richard L. Lewis and
Andrew G. Barto and
Jonathan Sorg},
title = {Intrinsically Motivated Reinforcement Learning: An Evolutionary Perspective},
journal = {{IEEE} Trans. Auton. Ment. Dev.},
volume = {2},
number = {2},
pages = {70--82},
year = {2010},
url = {https://doi.org/10.1109/TAMD.2010.2051031},
doi = {10.1109/TAMD.2010.2051031},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tamd/SinghLBS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SorgS10,
author = {Jonathan Sorg and
Satinder Singh},
editor = {Wiebe van der Hoek and
Gal A. Kaminka and
Yves Lesp{\'{e}}rance and
Michael Luck and
Sandip Sen},
title = {Linear options},
booktitle = {9th International Conference on Autonomous Agents and Multiagent Systems
{(AAMAS} 2010), Toronto, Canada, May 10-14, 2010, Volume 1-3},
pages = {31--38},
publisher = {{IFAAMAS}},
year = {2010},
url = {https://dl.acm.org/citation.cfm?id=1838211},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/SorgS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/DuongWSV10,
author = {Quang Duong and
Michael P. Wellman and
Satinder Singh and
Yevgeniy Vorobeychik},
editor = {Wiebe van der Hoek and
Gal A. Kaminka and
Yves Lesp{\'{e}}rance and
Michael Luck and
Sandip Sen},
title = {History-dependent graphical multiagent models},
booktitle = {9th International Conference on Autonomous Agents and Multiagent Systems
{(AAMAS} 2010), Toronto, Canada, May 10-14, 2010, Volume 1-3},
pages = {1215--1222},
publisher = {{IFAAMAS}},
year = {2010},
url = {https://dl.acm.org/citation.cfm?id=1838364},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/DuongWSV10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iat/CohnMDS10,
author = {Robert Cohn and
Michael Maxim and
Edmund H. Durfee and
Satinder Singh},
editor = {Jimmy Xiangji Huang and
Ali A. Ghorbani and
Mohand{-}Said Hacid and
Takahira Yamaguchi},
title = {Selecting Operator Queries Using Expected Myopic Gain},
booktitle = {Proceedings of the 2010 {IEEE/WIC/ACM} International Conference on
Intelligent Agent Technology, {IAT} 2010, Toronto, Canada, August
31 - September 3, 2010},
pages = {40--47},
publisher = {{IEEE} Computer Society Press},
year = {2010},
url = {https://doi.org/10.1109/WI-IAT.2010.142},
doi = {10.1109/WI-IAT.2010.142},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iat/CohnMDS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SorgSL10,
author = {Jonathan Sorg and
Satinder Singh and
Richard L. Lewis},
editor = {Johannes F{\"{u}}rnkranz and
Thorsten Joachims},
title = {Internal Rewards Mitigate Agent Boundedness},
booktitle = {Proceedings of the 27th International Conference on Machine Learning
(ICML-10), June 21-24, 2010, Haifa, Israel},
pages = {1007--1014},
publisher = {Omnipress},
year = {2010},
url = {https://icml.cc/Conferences/2010/papers/442.pdf},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/SorgSL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SorgSL10,
author = {Jonathan Sorg and
Satinder Singh and
Richard L. Lewis},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Reward Design via Online Gradient Ascent},
booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual
Conference on Neural Information Processing Systems 2010. Proceedings
of a meeting held 6-9 December 2010, Vancouver, British Columbia,
Canada},
pages = {2190--2198},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/168908dd3227b8358eababa07fcaf091-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/SorgSL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/SorgSL10,
author = {Jonathan Sorg and
Satinder Singh and
Richard L. Lewis},
editor = {Peter Gr{\"{u}}nwald and
Peter Spirtes},
title = {Variance-Based Rewards for Approximate Bayesian Reinforcement Learning},
booktitle = {{UAI} 2010, Proceedings of the Twenty-Sixth Conference on Uncertainty
in Artificial Intelligence, Catalina Island, CA, USA, July 8-11, 2010},
pages = {564--571},
publisher = {{AUAI} Press},
year = {2010},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=2150\&\#38;proceeding\_id=26},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/SorgSL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/JamesS09,
author = {Michael R. James and
Satinder Singh},
editor = {Carles Sierra and
Cristiano Castelfranchi and
Keith S. Decker and
Jaime Sim{\~{a}}o Sichman},
title = {SarsaLandmark: an algorithm for learning in POMDPs with landmarks},
booktitle = {8th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2009), Budapest, Hungary, May 10-15, 2009, Volume
1},
pages = {585--591},
publisher = {{IFAAMAS}},
year = {2009},
url = {https://dl.acm.org/citation.cfm?id=1558094},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/JamesS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SorgS09,
author = {Jonathan Sorg and
Satinder Singh},
editor = {Carles Sierra and
Cristiano Castelfranchi and
Keith S. Decker and
Jaime Sim{\~{a}}o Sichman},
title = {Transfer via soft homomorphisms},
booktitle = {8th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2009), Budapest, Hungary, May 10-15, 2009, Volume
2},
pages = {741--748},
publisher = {{IFAAMAS}},
year = {2009},
url = {https://dl.acm.org/citation.cfm?id=1558114},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/SorgS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/DuongVSW09,
author = {Quang Duong and
Yevgeniy Vorobeychik and
Satinder Singh and
Michael P. Wellman},
editor = {Craig Boutilier},
title = {Learning Graphical Game Models},
booktitle = {{IJCAI} 2009, Proceedings of the 21st International Joint Conference
on Artificial Intelligence, Pasadena, California, USA, July 11-17,
2009},
pages = {116--121},
year = {2009},
url = {http://ijcai.org/Proceedings/09/Papers/030.pdf},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/DuongVSW09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/TalvitieS09,
author = {Erik Talvitie and
Satinder Singh},
editor = {Craig Boutilier},
title = {Maintaining Predictions over Time without a Model},
booktitle = {{IJCAI} 2009, Proceedings of the 21st International Joint Conference
on Artificial Intelligence, Pasadena, California, USA, July 11-17,
2009},
pages = {1249--1254},
year = {2009},
url = {http://ijcai.org/Proceedings/09/Papers/210.pdf},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/TalvitieS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/WolfeJS08,
author = {Britton Wolfe and
Michael R. James and
Satinder Singh},
editor = {Lin Padgham and
David C. Parkes and
J{\"{o}}rg P. M{\"{u}}ller and
Simon Parsons},
title = {Approximate predictive state representations},
booktitle = {7th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2008), Estoril, Portugal, May 12-16, 2008, Volume
1},
pages = {363--370},
publisher = {{IFAAMAS}},
year = {2008},
url = {https://dl.acm.org/citation.cfm?id=1402437},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/WolfeJS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WingateS08,
author = {David Wingate and
Satinder Singh},
editor = {William W. Cohen and
Andrew McCallum and
Sam T. Roweis},
title = {Efficiently learning linear-linear exponential family predictive representations
of state},
booktitle = {Machine Learning, Proceedings of the Twenty-Fifth International Conference
{(ICML} 2008), Helsinki, Finland, June 5-9, 2008},
series = {{ACM} International Conference Proceeding Series},
volume = {307},
pages = {1176--1183},
publisher = {{ACM}},
year = {2008},
url = {https://doi.org/10.1145/1390156.1390304},
doi = {10.1145/1390156.1390304},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WingateS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isaim/RudaryS08,
author = {Matthew R. Rudary and
Satinder Singh},
title = {Predictive Linear-Gaussian Models of Dynamical Systems with Vector-Valued
Actions and Observations},
booktitle = {International Symposium on Artificial Intelligence and Mathematics,
{ISAIM} 2008, Fort Lauderdale, Florida, USA, January 2-4, 2008},
year = {2008},
url = {http://isaim2008.unl.edu/PAPERS/TechnicalProgram/ISAIM2008\_0042\_8f2d860dcc7387e100135b1737766088.pdf},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/isaim/RudaryS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isaim/TalvitieWS08,
author = {Erik Talvitie and
Britton Wolfe and
Satinder Singh},
title = {Building Incomplete but Accurate Models},
booktitle = {International Symposium on Artificial Intelligence and Mathematics,
{ISAIM} 2008, Fort Lauderdale, Florida, USA, January 2-4, 2008},
year = {2008},
url = {http://isaim2008.unl.edu/PAPERS/TechnicalProgram/ISAIM2008\_0037\_334f1e59f8f09d4cca350159a673fd78.pdf},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/isaim/TalvitieWS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/TalvitieS08,
author = {Erik Talvitie and
Satinder Singh},
editor = {Daphne Koller and
Dale Schuurmans and
Yoshua Bengio and
L{\'{e}}on Bottou},
title = {Simple Local Models for Complex Dynamical Systems},
booktitle = {Advances in Neural Information Processing Systems 21, Proceedings
of the Twenty-Second Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 8-11, 2008},
pages = {1617--1624},
publisher = {Curran Associates, Inc.},
year = {2008},
url = {https://proceedings.neurips.cc/paper/2008/hash/f76a89f0cb91bc419542ce9fa43902dc-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/TalvitieS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/DuongWS08,
author = {Quang Duong and
Michael P. Wellman and
Satinder Singh},
editor = {David A. McAllester and
Petri Myllym{\"{a}}ki},
title = {Knowledge Combination in Graphical Multiagent Models},
booktitle = {{UAI} 2008, Proceedings of the 24th Conference in Uncertainty in Artificial
Intelligence, Helsinki, Finland, July 9-12, 2008},
pages = {153--160},
publisher = {{AUAI} Press},
year = {2008},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=1947\&\#38;proceeding\_id=24},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/DuongWS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/VorobeychikWS07,
author = {Yevgeniy Vorobeychik and
Michael P. Wellman and
Satinder Singh},
title = {Learning payoff functions in infinite games},
journal = {Mach. Learn.},
volume = {67},
number = {1-2},
pages = {145--168},
year = {2007},
url = {https://doi.org/10.1007/s10994-007-0715-8},
doi = {10.1007/S10994-007-0715-8},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/VorobeychikWS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SoniS07,
author = {Vishal Soni and
Satinder Singh},
title = {Abstraction in Predictive State Representations},
booktitle = {Proceedings of the Twenty-Second {AAAI} Conference on Artificial Intelligence,
July 22-26, 2007, Vancouver, British Columbia, Canada},
pages = {639--644},
publisher = {{AAAI} Press},
year = {2007},
url = {http://www.aaai.org/Library/AAAI/2007/aaai07-101.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SoniS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/LiCYSJ07,
author = {Yunyao Li and
Ishan Chaudhuri and
Huahai Yang and
Satinder Singh and
H. V. Jagadish},
title = {Enabling Domain-Awareness for a Generic Natural Language Interface},
booktitle = {Proceedings of the Twenty-Second {AAAI} Conference on Artificial Intelligence,
July 22-26, 2007, Vancouver, British Columbia, Canada},
pages = {833--838},
publisher = {{AAAI} Press},
year = {2007},
url = {http://www.aaai.org/Library/AAAI/2007/aaai07-132.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/LiCYSJ07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SoniSW07,
author = {Vishal Soni and
Satinder Singh and
Michael P. Wellman},
editor = {Edmund H. Durfee and
Makoto Yokoo and
Michael N. Huhns and
Onn Shehory},
title = {Constraint satisfaction algorithms for graphical games},
booktitle = {6th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2007), Honolulu, Hawaii, USA, May 14-18, 2007},
pages = {67},
publisher = {{IFAAMAS}},
year = {2007},
url = {https://doi.org/10.1145/1329125.1329206},
doi = {10.1145/1329125.1329206},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/SoniSW07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/WingateS07,
author = {David Wingate and
Satinder Singh},
editor = {Edmund H. Durfee and
Makoto Yokoo and
Michael N. Huhns and
Onn Shehory},
title = {On discovery and learning of models with predictive representations
of state for agents with continuous actions and observations},
booktitle = {6th International Joint Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2007), Honolulu, Hawaii, USA, May 14-18, 2007},
pages = {187},
publisher = {{IFAAMAS}},
year = {2007},
url = {https://doi.org/10.1145/1329125.1329352},
doi = {10.1145/1329125.1329352},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/WingateS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/TalvitieS07,
author = {Erik Talvitie and
Satinder Singh},
editor = {Manuela M. Veloso},
title = {An Experts Algorithm for Transfer Learning},
booktitle = {{IJCAI} 2007, Proceedings of the 20th International Joint Conference
on Artificial Intelligence, Hyderabad, India, January 6-12, 2007},
pages = {1065--1070},
year = {2007},
url = {http://ijcai.org/Proceedings/07/Papers/172.pdf},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/TalvitieS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/WingateSWS07,
author = {David Wingate and
Vishal Soni and
Britton Wolfe and
Satinder Singh},
editor = {Manuela M. Veloso},
title = {Relational Knowledge with Predictive State Representations},
booktitle = {{IJCAI} 2007, Proceedings of the 20th International Joint Conference
on Artificial Intelligence, Hyderabad, India, January 6-12, 2007},
pages = {2035--2040},
year = {2007},
url = {http://ijcai.org/Proceedings/07/Papers/328.pdf},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/WingateSWS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WingateB07,
author = {David Wingate and
Satinder Singh},
editor = {John C. Platt and
Daphne Koller and
Yoram Singer and
Sam T. Roweis},
title = {Exponential Family Predictive Representations of State},
booktitle = {Advances in Neural Information Processing Systems 20, Proceedings
of the Twenty-First Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 3-6, 2007},
pages = {1617--1624},
publisher = {Curran Associates, Inc.},
year = {2007},
url = {https://proceedings.neurips.cc/paper/2007/hash/a9a1d5317a33ae8cef33961c34144f84-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/WingateB07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigmod/LiCYSJ07,
author = {Yunyao Li and
Ishan Chaudhuri and
Huahai Yang and
Satinder Singh and
H. V. Jagadish},
editor = {Chee Yong Chan and
Beng Chin Ooi and
Aoying Zhou},
title = {DaNaLIX: a domain-adaptive natural language interface for querying
{XML}},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management
of Data, Beijing, China, June 12-14, 2007},
pages = {1165--1168},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1247480.1247643},
doi = {10.1145/1247480.1247643},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sigmod/LiCYSJ07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/IsbellKSSSK06,
author = {Charles Lee Isbell Jr. and
Michael J. Kearns and
Satinder Singh and
Christian R. Shelton and
Peter Stone and
David P. Kormann},
title = {Cobot in LambdaMOO: An Adaptive Social Statistics Agent},
journal = {Auton. Agents Multi Agent Syst.},
volume = {13},
number = {3},
pages = {327--354},
year = {2006},
url = {https://doi.org/10.1007/s10458-006-0005-z},
doi = {10.1007/S10458-006-0005-Z},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aamas/IsbellKSSSK06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SoniS06,
author = {Vishal Soni and
Satinder Singh},
title = {Using Homomorphisms to Transfer Options across Continuous Reinforcement
Learning Domains},
booktitle = {Proceedings, The Twenty-First National Conference on Artificial Intelligence
and the Eighteenth Innovative Applications of Artificial Intelligence
Conference, July 16-20, 2006, Boston, Massachusetts, {USA}},
pages = {494--499},
publisher = {{AAAI} Press},
year = {2006},
url = {http://www.aaai.org/Library/AAAI/2006/aaai06-079.php},
timestamp = {Tue, 05 Sep 2023 09:10:47 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SoniS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/WingateS06,
author = {David Wingate and
Satinder Singh},
title = {Mixtures of Predictive Linear Gaussian Models for Nonlinear, Stochastic
Dynamical Systems},
booktitle = {Proceedings, The Twenty-First National Conference on Artificial Intelligence
and the Eighteenth Innovative Applications of Artificial Intelligence
Conference, July 16-20, 2006, Boston, Massachusetts, {USA}},
pages = {524--529},
publisher = {{AAAI} Press},
year = {2006},
url = {http://www.aaai.org/Library/AAAI/2006/aaai06-084.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/WingateS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/RudaryS06,
author = {Matthew R. Rudary and
Satinder Singh},
editor = {William W. Cohen and
Andrew W. Moore},
title = {Predictive linear-Gaussian models of controlled stochastic dynamical
systems},
booktitle = {Machine Learning, Proceedings of the Twenty-Third International Conference
{(ICML} 2006), Pittsburgh, Pennsylvania, USA, June 25-29, 2006},
series = {{ACM} International Conference Proceeding Series},
volume = {148},
pages = {777--784},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1143844.1143942},
doi = {10.1145/1143844.1143942},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/RudaryS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WingateS06,
author = {David Wingate and
Satinder Singh},
editor = {William W. Cohen and
Andrew W. Moore},
title = {Kernel Predictive Linear Gaussian models for nonlinear stochastic
dynamical systems},
booktitle = {Machine Learning, Proceedings of the Twenty-Third International Conference
{(ICML} 2006), Pittsburgh, Pennsylvania, USA, June 25-29, 2006},
series = {{ACM} International Conference Proceeding Series},
volume = {148},
pages = {1017--1024},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1143844.1143972},
doi = {10.1145/1143844.1143972},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WingateS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WolfeS06,
author = {Britton Wolfe and
Satinder Singh},
editor = {William W. Cohen and
Andrew W. Moore},
title = {Predictive state representations with options},
booktitle = {Machine Learning, Proceedings of the Twenty-Third International Conference
{(ICML} 2006), Pittsburgh, Pennsylvania, USA, June 25-29, 2006},
series = {{ACM} International Conference Proceeding Series},
volume = {148},
pages = {1025--1032},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1143844.1143973},
doi = {10.1145/1143844.1143973},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WolfeS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/CavalloPS06,
author = {Ruggiero Cavallo and
David C. Parkes and
Satinder Singh},
title = {Optimal Coordinated Planning Amongst Self-Interested Agents with Private
State},
booktitle = {{UAI} '06, Proceedings of the 22nd Conference in Uncertainty in Artificial
Intelligence, Cambridge, MA, USA, July 13-16, 2006},
publisher = {{AUAI} Press},
year = {2006},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=1300\&\#38;proceeding\_id=22},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/CavalloPS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aim/CassimatisLLGKEBSDLMSSLSAD05,
author = {Nicholas L. Cassimatis and
Sean Luke and
Simon D. Levy and
Ross W. Gayler and
Pentti Kanerva and
Chris Eliasmith and
Timothy W. Bickmore and
Alan C. Schultz and
Randall Davis and
James A. Landay and
Robert C. Miller and
Eric Saund and
Thomas F. Stahovich and
Michael L. Littman and
Satinder Singh and
Shlomo Argamon and
Shlomo Dubnov},
title = {Reports on the 2004 {AAAI} Fall Symposia},
journal = {{AI} Mag.},
volume = {26},
number = {1},
pages = {98--102},
year = {2005},
url = {https://doi.org/10.1609/aimag.v26i1.1805},
doi = {10.1609/AIMAG.V26I1.1805},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aim/CassimatisLLGKEBSDLMSSLSAD05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ci/WellmanESVKS05,
author = {Michael P. Wellman and
Joshua Estelle and
Satinder Singh and
Yevgeniy Vorobeychik and
Christopher Kiekintveld and
Vishal Soni},
title = {Strategic Interactions in a Supply Chain Game},
journal = {Comput. Intell.},
volume = {21},
number = {1},
pages = {1--26},
year = {2005},
url = {https://doi.org/10.1111/j.0824-7935.2005.00263.x},
doi = {10.1111/J.0824-7935.2005.00263.X},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ci/WellmanESVKS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/JamesS05,
author = {Michael R. James and
Satinder Singh},
editor = {Manuela M. Veloso and
Subbarao Kambhampati},
title = {Planning in Models that Combine Memory with Predictive Representations
of State},
booktitle = {Proceedings, The Twentieth National Conference on Artificial Intelligence
and the Seventeenth Innovative Applications of Artificial Intelligence
Conference, July 9-13, 2005, Pittsburgh, Pennsylvania, {USA}},
pages = {987--992},
publisher = {{AAAI} Press / The {MIT} Press},
year = {2005},
url = {http://www.aaai.org/Library/AAAI/2005/aaai05-156.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/JamesS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WolfeJS05,
author = {Britton Wolfe and
Michael R. James and
Satinder Singh},
editor = {Luc De Raedt and
Stefan Wrobel},
title = {Learning predictive state representations in dynamical systems without
reset},
booktitle = {Machine Learning, Proceedings of the Twenty-Second International Conference
{(ICML} 2005), Bonn, Germany, August 7-11, 2005},
series = {{ACM} International Conference Proceeding Series},
volume = {119},
pages = {980--987},
publisher = {{ACM}},
year = {2005},
url = {https://doi.org/10.1145/1102351.1102475},
doi = {10.1145/1102351.1102475},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WolfeJS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/JamesWS05,
author = {Michael R. James and
Britton Wolfe and
Satinder Singh},
editor = {Leslie Pack Kaelbling and
Alessandro Saffiotti},
title = {Combining Memory and Landmarks with Predictive State Representations},
booktitle = {IJCAI-05, Proceedings of the Nineteenth International Joint Conference
on Artificial Intelligence, Edinburgh, Scotland, UK, July 30 - August
5, 2005},
pages = {734--739},
publisher = {Professional Book Center},
year = {2005},
url = {http://ijcai.org/Proceedings/05/Papers/1621.pdf},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/JamesWS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/VorobeychikWS05,
author = {Yevgeniy Vorobeychik and
Michael P. Wellman and
Satinder Singh},
editor = {Leslie Pack Kaelbling and
Alessandro Saffiotti},
title = {Learning Payoff Functions in Infinite Games},
booktitle = {IJCAI-05, Proceedings of the Nineteenth International Joint Conference
on Artificial Intelligence, Edinburgh, Scotland, UK, July 30 - August
5, 2005},
pages = {977--982},
publisher = {Professional Book Center},
year = {2005},
url = {http://ijcai.org/Proceedings/05/Papers/0527.pdf},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/VorobeychikWS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/PrecupSPKS05,
author = {Doina Precup and
Richard S. Sutton and
Cosmin Paduraru and
Anna Koop and
Satinder Singh},
title = {Off-policy Learning with Options and Recognizers},
booktitle = {Advances in Neural Information Processing Systems 18 [Neural Information
Processing Systems, {NIPS} 2005, December 5-8, 2005, Vancouver, British
Columbia, Canada]},
pages = {1097--1104},
year = {2005},
url = {https://proceedings.neurips.cc/paper/2005/hash/f75526659f31040afeb61cb7133e4e6d-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/PrecupSPKS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/RudarySW05,
author = {Matthew R. Rudary and
Satinder Singh and
David Wingate},
title = {Predictive Linear-Gaussian Models of Stochastic Dynamical Systems},
booktitle = {{UAI} '05, Proceedings of the 21st Conference in Uncertainty in Artificial
Intelligence, Edinburgh, Scotland, July 26-29, 2005},
pages = {501--508},
publisher = {{AUAI} Press},
year = {2005},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=1187\&\#38;proceeding\_id=21},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/RudarySW05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sigecom/KiekintveldWSS04,
author = {Christopher Kiekintveld and
Michael P. Wellman and
Satinder Singh and
Vishal Soni},
title = {Value-driven procurement in the {TAC} supply chain game},
journal = {SIGecom Exch.},
volume = {4},
number = {3},
pages = {9--18},
year = {2004},
url = {https://doi.org/10.1145/1120701.1120704},
doi = {10.1145/1120701.1120704},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sigecom/KiekintveldWSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaifs/VorobeychikWS04,
author = {Yevgeniy Vorobeychik and
Michael P. Wellman and
Satinder Singh},
title = {Learning Payoff Functions in Infinite Games},
booktitle = {Artificial Multiagent Learning, Papers from the 2004 {AAAI} Fall Symposium.
Arlington, VA, USA, October 22-24, 2004},
volume = {{FS-04-02}},
pages = {60--65},
publisher = {{AAAI} Press},
year = {2004},
url = {https://www.aaai.org/Library/Symposia/Fall/2004/fs04-02-008.php},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaaifs/VorobeychikWS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aips/KiekintveldWSEVSR04,
author = {Christopher Kiekintveld and
Michael P. Wellman and
Satinder Singh and
Joshua Estelle and
Yevgeniy Vorobeychik and
Vishal Soni and
Matthew R. Rudary},
editor = {Shlomo Zilberstein and
Jana Koehler and
Sven Koenig},
title = {Distributed Feedback Control for Decision Making on Supply Chains},
booktitle = {Proceedings of the Fourteenth International Conference on Automated
Planning and Scheduling {(ICAPS} 2004), June 3-7 2004, Whistler, British
Columbia, Canada},
pages = {384--392},
publisher = {{AAAI}},
year = {2004},
url = {http://www.aaai.org/Library/ICAPS/2004/icaps04-045.php},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aips/KiekintveldWSEVSR04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cg/EstelleVWSKS04,
author = {Joshua Estelle and
Yevgeniy Vorobeychik and
Michael P. Wellman and
Satinder Singh and
Christopher Kiekintveld and
Vishal Soni},
editor = {H. Jaap van den Herik and
Yngvi Bj{\"{o}}rnsson and
Nathan S. Netanyahu},
title = {Strategic Interactions in the {TAC} 2003 Supply Chain Tournament},
booktitle = {Computers and Games, 4th International Conference, {CG} 2004, Ramat-Gan,
Israel, July 5-7, 2004, Revised Papers},
series = {Lecture Notes in Computer Science},
volume = {3846},
pages = {316--331},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/11674399\_22},
doi = {10.1007/11674399\_22},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cg/EstelleVWSKS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/JamesS04,
author = {Michael R. James and
Satinder Singh},
editor = {Carla E. Brodley},
title = {Learning and discovery of predictive state representations in dynamical
systems with reset},
booktitle = {Machine Learning, Proceedings of the Twenty-first International Conference
{(ICML} 2004), Banff, Alberta, Canada, July 4-8, 2004},
series = {{ACM} International Conference Proceeding Series},
volume = {69},
publisher = {{ACM}},
year = {2004},
url = {https://doi.org/10.1145/1015330.1015359},
doi = {10.1145/1015330.1015359},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/JamesS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/RudarySP04,
author = {Matthew R. Rudary and
Satinder Singh and
Martha E. Pollack},
editor = {Carla E. Brodley},
title = {Adaptive cognitive orthotics: combining reinforcement learning and
constraint-based temporal reasoning},
booktitle = {Machine Learning, Proceedings of the Twenty-first International Conference
{(ICML} 2004), Banff, Alberta, Canada, July 4-8, 2004},
series = {{ACM} International Conference Proceeding Series},
volume = {69},
publisher = {{ACM}},
year = {2004},
url = {https://doi.org/10.1145/1015330.1015411},
doi = {10.1145/1015330.1015411},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/RudarySP04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmla/JamesSL04,
author = {Michael R. James and
Satinder Singh and
Michael L. Littman},
editor = {Mehmed M. Kantardzic and
Mariofanna G. Milanova and
Olfa Nasraoui},
title = {Planning with predictive state representations},
booktitle = {Proceedings of the 2004 International Conference on Machine Learning
and Applications - {ICMLA} 2004, 16-18 December 2004, Louisville,
KY, {USA}},
pages = {304--311},
publisher = {{IEEE} Computer Society},
year = {2004},
url = {https://doi.org/10.1109/ICMLA.2004.1383528},
doi = {10.1109/ICMLA.2004.1383528},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icmla/JamesSL04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ParkesSY04,
author = {David C. Parkes and
Satinder Singh and
Dimah Yanovsky},
title = {Approximately Efficient Online Mechanism Design},
booktitle = {Advances in Neural Information Processing Systems 17 [Neural Information
Processing Systems, {NIPS} 2004, December 13-18, 2004, Vancouver,
British Columbia, Canada]},
pages = {1049--1056},
year = {2004},
url = {https://proceedings.neurips.cc/paper/2004/hash/fc03d48253286a798f5116ec00e99b2b-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/ParkesSY04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SinghBC04,
author = {Satinder Singh and
Andrew G. Barto and
Nuttapong Chentanez},
title = {Intrinsically Motivated Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 17 [Neural Information
Processing Systems, {NIPS} 2004, December 13-18, 2004, Vancouver,
British Columbia, Canada]},
pages = {1281--1288},
year = {2004},
url = {https://proceedings.neurips.cc/paper/2004/hash/4be5a36cbaca8ab9d2066debfe4e65c1-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/SinghBC04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigecom/SinghSW04,
author = {Satinder Singh and
Vishal Soni and
Michael P. Wellman},
editor = {Jack S. Breese and
Joan Feigenbaum and
Margo I. Seltzer},
title = {Computing approximate bayes-nash equilibria in tree-games of incomplete
information},
booktitle = {Proceedings 5th {ACM} Conference on Electronic Commerce (EC-2004),
New York, NY, USA, May 17-20, 2004},
pages = {81--90},
publisher = {{ACM}},
year = {2004},
url = {https://doi.org/10.1145/988772.988785},
doi = {10.1145/988772.988785},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sigecom/SinghSW04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/SinghJR04,
author = {Satinder Singh and
Michael R. James and
Matthew R. Rudary},
editor = {David Maxwell Chickering and
Joseph Y. Halpern},
title = {Predictive State Representations: {A} New Theory for Modeling Dynamical
Systems},
booktitle = {{UAI} '04, Proceedings of the 20th Conference in Uncertainty in Artificial
Intelligence, Banff, Canada, July 7-11, 2004},
pages = {512--518},
publisher = {{AUAI} Press},
year = {2004},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=1148\&\#38;proceeding\_id=20},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/SinghJR04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SinghLJPS03,
author = {Satinder Singh and
Michael L. Littman and
Nicholas K. Jong and
David Pardoe and
Peter Stone},
editor = {Tom Fawcett and
Nina Mishra},
title = {Learning Predictive State Representations},
booktitle = {Machine Learning, Proceedings of the Twentieth International Conference
{(ICML} 2003), August 21-24, 2003, Washington, DC, {USA}},
pages = {712--719},
publisher = {{AAAI} Press},
year = {2003},
url = {http://www.aaai.org/Library/ICML/2003/icml03-093.php},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/SinghLJPS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ParkesS03,
author = {David C. Parkes and
Satinder Singh},
editor = {Sebastian Thrun and
Lawrence K. Saul and
Bernhard Sch{\"{o}}lkopf},
title = {An MDP-Based Approach to Online Mechanism Design},
booktitle = {Advances in Neural Information Processing Systems 16 [Neural Information
Processing Systems, {NIPS} 2003, December 8-13, 2003, Vancouver and
Whistler, British Columbia, Canada]},
pages = {791--798},
publisher = {{MIT} Press},
year = {2003},
url = {https://proceedings.neurips.cc/paper/2003/hash/d16509f6eaca1022bd8f28d6bc582cae-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/ParkesS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/RudaryS03,
author = {Matthew R. Rudary and
Satinder Singh},
editor = {Sebastian Thrun and
Lawrence K. Saul and
Bernhard Sch{\"{o}}lkopf},
title = {A Nonlinear Predictive State Representation},
booktitle = {Advances in Neural Information Processing Systems 16 [Neural Information
Processing Systems, {NIPS} 2003, December 8-13, 2003, Vancouver and
Whistler, British Columbia, Canada]},
pages = {855--862},
publisher = {{MIT} Press},
year = {2003},
url = {https://proceedings.neurips.cc/paper/2003/hash/72e6d3238361fe70f22fb0ac624a7072-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/RudaryS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/SinghLKW02,
author = {Satinder Singh and
Diane J. Litman and
Michael J. Kearns and
Marilyn A. Walker},
title = {Optimizing Dialogue Management with Reinforcement Learning: Experiments
with the NJFun System},
journal = {J. Artif. Intell. Res.},
volume = {16},
pages = {105--133},
year = {2002},
url = {https://doi.org/10.1613/jair.859},
doi = {10.1613/JAIR.859},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jair/SinghLKW02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/Singh02,
author = {Satinder Singh},
title = {Introduction},
journal = {Mach. Learn.},
volume = {49},
number = {2-3},
pages = {107--109},
year = {2002},
url = {https://doi.org/10.1023/A:1017917511082},
doi = {10.1023/A:1017917511082},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/Singh02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/KearnsS02,
author = {Michael J. Kearns and
Satinder Singh},
title = {Near-Optimal Reinforcement Learning in Polynomial Time},
journal = {Mach. Learn.},
volume = {49},
number = {2-3},
pages = {209--232},
year = {2002},
url = {https://doi.org/10.1023/A:1017984413808},
doi = {10.1023/A:1017984413808},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/KearnsS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/KearnsISLH02,
author = {Michael J. Kearns and
Charles Lee Isbell Jr. and
Satinder Singh and
Diane J. Litman and
Jessica Howe},
editor = {Rina Dechter and
Michael J. Kearns and
Richard S. Sutton},
title = {CobotDS: {A} Spoken Dialogue System for Chat},
booktitle = {Proceedings of the Eighteenth National Conference on Artificial Intelligence
and Fourteenth Conference on Innovative Applications of Artificial
Intelligence, July 28 - August 1, 2002, Edmonton, Alberta, Canada},
pages = {425--430},
publisher = {{AAAI} Press / The {MIT} Press},
year = {2002},
url = {http://www.aaai.org/Library/AAAI/2002/aaai02-065.php},
timestamp = {Tue, 05 Sep 2023 09:10:47 +0200},
biburl = {https://dblp.org/rec/conf/aaai/KearnsISLH02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/StoneLSK01,
author = {Peter Stone and
Michael L. Littman and
Satinder Singh and
Michael J. Kearns},
title = {ATTac-2000: An Adaptive Autonomous Bidding Agent},
journal = {J. Artif. Intell. Res.},
volume = {15},
pages = {189--206},
year = {2001},
url = {https://doi.org/10.1613/jair.865},
doi = {10.1613/JAIR.865},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jair/StoneLSK01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/agents/StoneLSK01,
author = {Peter Stone and
Michael L. Littman and
Satinder Singh and
Michael J. Kearns},
editor = {Elisabeth Andr{\'{e}} and
Sandip Sen and
Claude Frasson and
J{\"{o}}rg P. M{\"{u}}ller},
title = {ATTac-2000: an adaptive autonomous bidding agent},
booktitle = {Proceedings of the Fifth International Conference on Autonomous Agents,
{AGENTS} 2001, Montreal, Canada, May 28 - June 1, 2001},
pages = {238--245},
publisher = {{ACM}},
year = {2001},
url = {https://doi.org/10.1145/375735.376301},
doi = {10.1145/375735.376301},
timestamp = {Sat, 30 Sep 2023 09:33:47 +0200},
biburl = {https://dblp.org/rec/conf/agents/StoneLSK01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/agents/IsbellSKSS01,
author = {Charles Lee Isbell Jr. and
Christian R. Shelton and
Michael J. Kearns and
Satinder Singh and
Peter Stone},
editor = {Elisabeth Andr{\'{e}} and
Sandip Sen and
Claude Frasson and
J{\"{o}}rg P. M{\"{u}}ller},
title = {A social reinforcement learning agent},
booktitle = {Proceedings of the Fifth International Conference on Autonomous Agents,
{AGENTS} 2001, Montreal, Canada, May 28 - June 1, 2001},
pages = {377--384},
publisher = {{ACM}},
year = {2001},
url = {https://doi.org/10.1145/375735.376334},
doi = {10.1145/375735.376334},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/agents/IsbellSKSS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LittmanKS01,
author = {Michael L. Littman and
Michael J. Kearns and
Satinder Singh},
editor = {Thomas G. Dietterich and
Suzanna Becker and
Zoubin Ghahramani},
title = {An Efficient, Exact Algorithm for Solving Tree-Structured Graphical
Games},
booktitle = {Advances in Neural Information Processing Systems 14 [Neural Information
Processing Systems: Natural and Synthetic, {NIPS} 2001, December 3-8,
2001, Vancouver, British Columbia, Canada]},
pages = {817--823},
publisher = {{MIT} Press},
year = {2001},
url = {https://proceedings.neurips.cc/paper/2001/hash/c5866e93cab1776890fe343c9e7063fb-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/LittmanKS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/IsbellSKSS01,
author = {Charles Lee Isbell Jr. and
Christian R. Shelton and
Michael J. Kearns and
Satinder Singh and
Peter Stone},
editor = {Thomas G. Dietterich and
Suzanna Becker and
Zoubin Ghahramani},
title = {Cobot: {A} Social Reinforcement Learning Agent},
booktitle = {Advances in Neural Information Processing Systems 14 [Neural Information
Processing Systems: Natural and Synthetic, {NIPS} 2001, December 3-8,
2001, Vancouver, British Columbia, Canada]},
pages = {1393--1400},
publisher = {{MIT} Press},
year = {2001},
url = {https://proceedings.neurips.cc/paper/2001/hash/92bbd31f8e0e43a7da8a6295b251725f-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/IsbellSKSS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LittmanSS01,
author = {Michael L. Littman and
Richard S. Sutton and
Satinder Singh},
editor = {Thomas G. Dietterich and
Suzanna Becker and
Zoubin Ghahramani},
title = {Predictive Representations of State},
booktitle = {Advances in Neural Information Processing Systems 14 [Neural Information
Processing Systems: Natural and Synthetic, {NIPS} 2001, December 3-8,
2001, Vancouver, British Columbia, Canada]},
pages = {1555--1561},
publisher = {{MIT} Press},
year = {2001},
url = {https://proceedings.neurips.cc/paper/2001/hash/1e4d36177d71bbb3558e43af9577d70e-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/LittmanSS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/KearnsLS01,
author = {Michael J. Kearns and
Michael L. Littman and
Satinder Singh},
editor = {Jack S. Breese and
Daphne Koller},
title = {Graphical Models for Game Theory},
booktitle = {{UAI} '01: Proceedings of the 17th Conference in Uncertainty in Artificial
Intelligence, University of Washington, Seattle, Washington, USA,
August 2-5, 2001},
pages = {253--260},
publisher = {Morgan Kaufmann},
year = {2001},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=107\&\#38;proceeding\_id=17},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/KearnsLS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/welcom/CsirikLSS01,
author = {J{\'{a}}nos A. Csirik and
Michael L. Littman and
Satinder Singh and
Peter Stone},
editor = {Ludger Fiege and
Gero M{\"{u}}hl and
Uwe G. Wilhelm},
title = {FAucS : An {FCC} Spectrum Auction Simulator for Autonomous Bidding
Agents},
booktitle = {Electronic Commerce, Second International Workshop, {WELCOM} 2001
Heidelberg, Germany, November 16-17, 2001, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2232},
pages = {139--151},
publisher = {Springer},
year = {2001},
url = {https://doi.org/10.1007/3-540-45598-1\_14},
doi = {10.1007/3-540-45598-1\_14},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/welcom/CsirikLSS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/SinghJLS00,
author = {Satinder Singh and
Tommi S. Jaakkola and
Michael L. Littman and
Csaba Szepesv{\'{a}}ri},
title = {Convergence Results for Single-Step On-Policy Reinforcement-Learning
Algorithms},
journal = {Mach. Learn.},
volume = {38},
number = {3},
pages = {287--308},
year = {2000},
url = {https://doi.org/10.1023/A:1007678930559},
doi = {10.1023/A:1007678930559},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/SinghJLS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/IsbellKKSS00,
author = {Charles Lee Isbell Jr. and
Michael J. Kearns and
David P. Kormann and
Satinder Singh and
Peter Stone},
editor = {Henry A. Kautz and
Bruce W. Porter},
title = {Cobot in LambdaMOO: {A} Social Statistics Agent},
booktitle = {Proceedings of the Seventeenth National Conference on Artificial Intelligence
and Twelfth Conference on on Innovative Applications of Artificial
Intelligence, July 30 - August 3, 2000, Austin, Texas, {USA}},
pages = {36--41},
publisher = {{AAAI} Press / The {MIT} Press},
year = {2000},
url = {http://www.aaai.org/Library/AAAI/2000/aaai00-006.php},
timestamp = {Tue, 05 Sep 2023 09:10:47 +0200},
biburl = {https://dblp.org/rec/conf/aaai/IsbellKKSS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SinghKLW00,
author = {Satinder Singh and
Michael J. Kearns and
Diane J. Litman and
Marilyn A. Walker},
editor = {Henry A. Kautz and
Bruce W. Porter},
title = {Empirical Evaluation of a Reinforcement Learning Spoken Dialogue System},
booktitle = {Proceedings of the Seventeenth National Conference on Artificial Intelligence
and Twelfth Conference on on Innovative Applications of Artificial
Intelligence, July 30 - August 3, 2000, Austin, Texas, {USA}},
pages = {645--651},
publisher = {{AAAI} Press / The {MIT} Press},
year = {2000},
url = {http://www.aaai.org/Library/AAAI/2000/aaai00-099.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SinghKLW00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/coling/LitmanKSW00,
author = {Diane J. Litman and
Michael S. Kearns and
Satinder Singh and
Marilyn A. Walker},
title = {Automatic Optimization of Dialogue Management},
booktitle = {{COLING} 2000, 18th International Conference on Computational Linguistics,
Proceedings of the Conference, 2 Volumes, July 31 - August 4, 2000,
Universit{\"{a}}t des Saarlandes, Saarbr{\"{u}}cken, Germany},
pages = {502--508},
publisher = {Morgan Kaufmann},
year = {2000},
url = {https://aclanthology.org/C00-1073/},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/coling/LitmanKSW00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/KearnsS00,
author = {Michael J. Kearns and
Satinder Singh},
editor = {Nicol{\`{o}} Cesa{-}Bianchi and
Sally A. Goldman},
title = {Bias-Variance Error Bounds for Temporal Difference Updates},
booktitle = {Proceedings of the Thirteenth Annual Conference on Computational Learning
Theory {(COLT} 2000), June 28 - July 1, 2000, Palo Alto, California,
{USA}},
pages = {142--147},
publisher = {Morgan Kaufmann},
year = {2000},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/KearnsS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MyersKSW00,
author = {Kary L. Myers and
Michael J. Kearns and
Satinder Singh and
Marilyn A. Walker},
editor = {Pat Langley},
title = {A Boosting Approach to Topic Spotting on Subdialogues},
booktitle = {Proceedings of the Seventeenth International Conference on Machine
Learning {(ICML} 2000), Stanford University, Stanford, CA, USA, June
29 - July 2, 2000},
pages = {655--662},
publisher = {Morgan Kaufmann},
year = {2000},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MyersKSW00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/PrecupSS00,
author = {Doina Precup and
Richard S. Sutton and
Satinder Singh},
editor = {Pat Langley},
title = {Eligibility Traces for Off-Policy Policy Evaluation},
booktitle = {Proceedings of the Seventeenth International Conference on Machine
Learning {(ICML} 2000), Stanford University, Stanford, CA, USA, June
29 - July 2, 2000},
pages = {759--766},
publisher = {Morgan Kaufmann},
year = {2000},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/PrecupSS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocup/StoneSS00,
author = {Peter Stone and
Richard S. Sutton and
Satinder Singh},
editor = {Peter Stone and
Tucker R. Balch and
Gerhard K. Kraetzschmar},
title = {Reinforcement Learning for 3 vs. 2 Keepaway},
booktitle = {RoboCup 2000: Robot Soccer World Cup {IV}},
series = {Lecture Notes in Computer Science},
volume = {2019},
pages = {249--258},
publisher = {Springer},
year = {2000},
url = {https://doi.org/10.1007/3-540-45324-5\_23},
doi = {10.1007/3-540-45324-5\_23},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/robocup/StoneSS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/KearnsMS00,
author = {Michael J. Kearns and
Yishay Mansour and
Satinder Singh},
editor = {Craig Boutilier and
Mois{\'{e}}s Goldszmidt},
title = {Fast Planning in Stochastic Games},
booktitle = {{UAI} '00: Proceedings of the 16th Conference in Uncertainty in Artificial
Intelligence, Stanford University, Stanford, California, USA, June
30 - July 3, 2000},
pages = {309--316},
publisher = {Morgan Kaufmann},
year = {2000},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=37\&\#38;proceeding\_id=16},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/KearnsMS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/SinghKM00,
author = {Satinder Singh and
Michael J. Kearns and
Yishay Mansour},
editor = {Craig Boutilier and
Mois{\'{e}}s Goldszmidt},
title = {Nash Convergence of Gradient Dynamics in General-Sum Games},
booktitle = {{UAI} '00: Proceedings of the 16th Conference in Uncertainty in Artificial
Intelligence, Stanford University, Stanford, California, USA, June
30 - July 3, 2000},
pages = {541--548},
publisher = {Morgan Kaufmann},
year = {2000},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=63\&\#38;proceeding\_id=16},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/SinghKM00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ai/SuttonPS99,
author = {Richard S. Sutton and
Doina Precup and
Satinder Singh},
title = {Between MDPs and Semi-MDPs: {A} Framework for Temporal Abstraction
in Reinforcement Learning},
journal = {Artif. Intell.},
volume = {112},
number = {1-2},
pages = {181--211},
year = {1999},
url = {https://doi.org/10.1016/S0004-3702(99)00052-1},
doi = {10.1016/S0004-3702(99)00052-1},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ai/SuttonPS99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SinghKLW99,
author = {Satinder Singh and
Michael J. Kearns and
Diane J. Litman and
Marilyn A. Walker},
editor = {Sara A. Solla and
Todd K. Leen and
Klaus{-}Robert M{\"{u}}ller},
title = {Reinforcement Learning for Spoken Dialogue Systems},
booktitle = {Advances in Neural Information Processing Systems 12, {[NIPS} Conference,
Denver, Colorado, USA, November 29 - December 4, 1999]},
pages = {956--962},
publisher = {The {MIT} Press},
year = {1999},
url = {http://papers.nips.cc/paper/1775-reinforcement-learning-for-spoken-dialogue-systems},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/SinghKLW99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SuttonMSM99,
author = {Richard S. Sutton and
David A. McAllester and
Satinder Singh and
Yishay Mansour},
editor = {Sara A. Solla and
Todd K. Leen and
Klaus{-}Robert M{\"{u}}ller},
title = {Policy Gradient Methods for Reinforcement Learning with Function Approximation},
booktitle = {Advances in Neural Information Processing Systems 12, {[NIPS} Conference,
Denver, Colorado, USA, November 29 - December 4, 1999]},
pages = {1057--1063},
publisher = {The {MIT} Press},
year = {1999},
url = {http://papers.nips.cc/paper/1713-policy-gradient-methods-for-reinforcement-learning-with-function-approximation},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/SuttonMSM99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/MansourS99,
author = {Yishay Mansour and
Satinder Singh},
editor = {Kathryn B. Laskey and
Henri Prade},
title = {On the Complexity of Policy Iteration},
booktitle = {{UAI} '99: Proceedings of the Fifteenth Conference on Uncertainty
in Artificial Intelligence, Stockholm, Sweden, July 30 - August 1,
1999},
pages = {401--408},
publisher = {Morgan Kaufmann},
year = {1999},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=192\&\#38;proceeding\_id=15},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/MansourS99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/McAllesterS99,
author = {David A. McAllester and
Satinder Singh},
editor = {Kathryn B. Laskey and
Henri Prade},
title = {Approximate Planning for Factored POMDPs using Belief State Simplification},
booktitle = {{UAI} '99: Proceedings of the Fifteenth Conference on Uncertainty
in Artificial Intelligence, Stockholm, Sweden, July 30 - August 1,
1999},
pages = {409--416},
publisher = {Morgan Kaufmann},
year = {1999},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=193\&\#38;proceeding\_id=15},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/McAllesterS99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/SinghD98,
author = {Satinder Singh and
Peter Dayan},
title = {Analytical Mean Squared Error Curves for Temporal Difference Learning},
journal = {Mach. Learn.},
volume = {32},
number = {1},
pages = {5--40},
year = {1998},
url = {https://doi.org/10.1023/A:1007495401240},
doi = {10.1023/A:1007495401240},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/SinghD98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecml/PrecupSS98,
author = {Doina Precup and
Richard S. Sutton and
Satinder Singh},
editor = {Claire Nedellec and
C{\'{e}}line Rouveirol},
title = {Theoretical Results on Reinforcement Learning with Temporally Abstract
Options},
booktitle = {Machine Learning: ECML-98, 10th European Conference on Machine Learning,
Chemnitz, Germany, April 21-23, 1998, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1398},
pages = {382--393},
publisher = {Springer},
year = {1998},
url = {https://doi.org/10.1007/BFb0026709},
doi = {10.1007/BFB0026709},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ecml/PrecupSS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KearnsS98,
author = {Michael J. Kearns and
Satinder Singh},
editor = {Jude W. Shavlik},
title = {Near-Optimal Reinforcement Learning in Polynominal Time},
booktitle = {Proceedings of the Fifteenth International Conference on Machine Learning
{(ICML} 1998), Madison, Wisconsin, USA, July 24-27, 1998},
pages = {260--268},
publisher = {Morgan Kaufmann},
year = {1998},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/KearnsS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LochS98,
author = {John Loch and
Satinder Singh},
editor = {Jude W. Shavlik},
title = {Using Eligibility Traces to Find the Best Memoryless Policy in Partially
Observable Markov Decision Processes},
booktitle = {Proceedings of the Fifteenth International Conference on Machine Learning
{(ICML} 1998), Madison, Wisconsin, USA, July 24-27, 1998},
pages = {323--331},
publisher = {Morgan Kaufmann},
year = {1998},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/LochS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SuttonPS98,
author = {Richard S. Sutton and
Doina Precup and
Satinder Singh},
editor = {Jude W. Shavlik},
title = {Intra-Option Learning about Temporally Abstract Actions},
booktitle = {Proceedings of the Fifteenth International Conference on Machine Learning
{(ICML} 1998), Madison, Wisconsin, USA, July 24-27, 1998},
pages = {556--564},
publisher = {Morgan Kaufmann},
year = {1998},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/SuttonPS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BrownTS98,
author = {Timothy X. Brown and
Hui Tong and
Satinder Singh},
editor = {Michael J. Kearns and
Sara A. Solla and
David A. Cohn},
title = {Optimizing Admission Control while Ensuring Quality of Service in
Multimedia Networks via Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 11, {[NIPS} Conference,
Denver, Colorado, USA, November 30 - December 5, 1998]},
pages = {982--988},
publisher = {The {MIT} Press},
year = {1998},
url = {http://papers.nips.cc/paper/1599-optimizing-admission-control-while-ensuring-quality-of-service-in-multimedia-networks-via-reinforcement-learning},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/BrownTS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KearnsS98a,
author = {Michael J. Kearns and
Satinder Singh},
editor = {Michael J. Kearns and
Sara A. Solla and
David A. Cohn},
title = {Finite-Sample Convergence Rates for Q-Learning and Indirect Algorithms},
booktitle = {Advances in Neural Information Processing Systems 11, {[NIPS} Conference,
Denver, Colorado, USA, November 30 - December 5, 1998]},
pages = {996--1002},
publisher = {The {MIT} Press},
year = {1998},
url = {http://papers.nips.cc/paper/1531-finite-sample-convergence-rates-for-q-learning-and-indirect-algorithms},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/KearnsS98a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SuttonSPR98,
author = {Richard S. Sutton and
Satinder Singh and
Doina Precup and
Balaraman Ravindran},
editor = {Michael J. Kearns and
Sara A. Solla and
David A. Cohn},
title = {Improved Switching among Temporally Abstract Actions},
booktitle = {Advances in Neural Information Processing Systems 11, {[NIPS} Conference,
Denver, Colorado, USA, November 30 - December 5, 1998]},
pages = {1066--1072},
publisher = {The {MIT} Press},
year = {1998},
url = {http://papers.nips.cc/paper/1607-improved-switching-among-temporally-abstract-actions},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/SuttonSPR98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WilliamsS98,
author = {John K. Williams and
Satinder Singh},
editor = {Michael J. Kearns and
Sara A. Solla and
David A. Cohn},
title = {Experimental Results on Learning Stochastic Memoryless Policies for
Partially Observable Markov Decision Processes},
booktitle = {Advances in Neural Information Processing Systems 11, {[NIPS} Conference,
Denver, Colorado, USA, November 30 - December 5, 1998]},
pages = {1073--1080},
publisher = {The {MIT} Press},
year = {1998},
url = {http://papers.nips.cc/paper/1509-experimental-results-on-learning-stochastic-memoryless-policies-for-partially-observable-markov-decision-processes},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/WilliamsS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SinghC97,
author = {Satinder Singh and
David Cohn},
editor = {Michael I. Jordan and
Michael J. Kearns and
Sara A. Solla},
title = {How to Dynamically Merge Markov Decision Processes},
booktitle = {Advances in Neural Information Processing Systems 10, {[NIPS} Conference,
Denver, Colorado, USA, 1997]},
pages = {1057--1063},
publisher = {The {MIT} Press},
year = {1997},
url = {http://papers.nips.cc/paper/1420-how-to-dynamically-merge-markov-decision-processes},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/SinghC97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/SinghS96,
author = {Satinder P. Singh and
Richard S. Sutton},
title = {Reinforcement Learning with Replacing Eligibility Traces},
journal = {Mach. Learn.},
volume = {22},
number = {1-3},
pages = {123--158},
year = {1996},
url = {https://doi.org/10.1023/A:1018012322525},
doi = {10.1023/A:1018012322525},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/SinghS96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/SaulS96,
author = {Lawrence K. Saul and
Satinder P. Singh},
editor = {Avrim Blum and
Michael J. Kearns},
title = {Learning Curve Bounds for a Markov Decision Process with Undiscounted
Rewards},
booktitle = {Proceedings of the Ninth Annual Conference on Computational Learning
Theory, {COLT} 1996, Desenzano del Garda, Italy, June 28-July 1, 1996},
pages = {147--156},
publisher = {{ACM}},
year = {1996},
url = {https://doi.org/10.1145/238061.238084},
doi = {10.1145/238061.238084},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/SaulS96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/CohnS96,
author = {David A. Cohn and
Satinder Singh},
editor = {Michael Mozer and
Michael I. Jordan and
Thomas Petsche},
title = {Predicting Lifetimes in Dynamically Allocated Memory},
booktitle = {Advances in Neural Information Processing Systems 9, NIPS, Denver,
CO, USA, December 2-5, 1996},
pages = {939--945},
publisher = {{MIT} Press},
year = {1996},
url = {http://papers.nips.cc/paper/1240-predicting-lifetimes-in-dynamically-allocated-memory},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/CohnS96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SinghB96,
author = {Satinder Singh and
Dimitri P. Bertsekas},
editor = {Michael Mozer and
Michael I. Jordan and
Thomas Petsche},
title = {Reinforcement Learning for Dynamic Channel Allocation in Cellular
Telephone Systems},
booktitle = {Advances in Neural Information Processing Systems 9, NIPS, Denver,
CO, USA, December 2-5, 1996},
pages = {974--980},
publisher = {{MIT} Press},
year = {1996},
url = {http://papers.nips.cc/paper/1216-reinforcement-learning-for-dynamic-channel-allocation-in-cellular-telephone-systems},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/SinghB96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SinghD96,
author = {Satinder Singh and
Peter Dayan},
editor = {Michael Mozer and
Michael I. Jordan and
Thomas Petsche},
title = {Analytical Mean Squared Error Curves in Temporal Difference Learning},
booktitle = {Advances in Neural Information Processing Systems 9, NIPS, Denver,
CO, USA, December 2-5, 1996},
pages = {1054--1060},
publisher = {{MIT} Press},
year = {1996},
url = {http://papers.nips.cc/paper/1284-analytical-mean-squared-error-curves-in-temporal-difference-learning},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/SinghD96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ai/BartoBS95,
author = {Andrew G. Barto and
Steven J. Bradtke and
Satinder P. Singh},
title = {Learning to Act Using Real-Time Dynamic Programming},
journal = {Artif. Intell.},
volume = {72},
number = {1-2},
pages = {81--138},
year = {1995},
url = {https://doi.org/10.1016/0004-3702(94)00011-O},
doi = {10.1016/0004-3702(94)00011-O},
timestamp = {Sat, 27 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ai/BartoBS95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/SaulS95,
author = {Lawrence K. Saul and
Satinder P. Singh},
editor = {Wolfgang Maass},
title = {Markov Decision Processes in Large State Spaces},
booktitle = {Proceedings of the Eigth Annual Conference on Computational Learning
Theory, {COLT} 1995, Santa Cruz, California, USA, July 5-8, 1995},
pages = {281--288},
publisher = {{ACM}},
year = {1995},
url = {https://doi.org/10.1145/225298.225332},
doi = {10.1145/225298.225332},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/SaulS95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/DayanS95,
author = {Peter Dayan and
Satinder Singh},
editor = {David S. Touretzky and
Michael Mozer and
Michael E. Hasselmo},
title = {Improving Policies without Measuring Merits},
booktitle = {Advances in Neural Information Processing Systems 8, NIPS, Denver,
CO, USA, November 27-30, 1995},
pages = {1059--1065},
publisher = {{MIT} Press},
year = {1995},
url = {http://papers.nips.cc/paper/1143-improving-policies-without-measuring-merits},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/DayanS95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/SinghY94,
author = {Satinder P. Singh and
Richard C. Yee},
title = {An Upper Bound on the Loss from Approximate Optimal-Value Functions},
journal = {Mach. Learn.},
volume = {16},
number = {3},
pages = {227--233},
year = {1994},
url = {https://doi.org/10.1007/BF00993308},
doi = {10.1007/BF00993308},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/SinghY94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/neco/JaakkolaJS94,
author = {Tommi S. Jaakkola and
Michael I. Jordan and
Satinder P. Singh},
title = {On the Convergence of Stochastic Iterative Dynamic Programming Algorithms},
journal = {Neural Comput.},
volume = {6},
number = {6},
pages = {1185--1201},
year = {1994},
url = {https://doi.org/10.1162/neco.1994.6.6.1185},
doi = {10.1162/NECO.1994.6.6.1185},
timestamp = {Tue, 01 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/neco/JaakkolaJS94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/Singh94,
author = {Satinder P. Singh},
editor = {Barbara Hayes{-}Roth and
Richard E. Korf},
title = {Reinforcement Learning Algorithms for Average-Payoff Markovian Decision
Processes},
booktitle = {Proceedings of the 12th National Conference on Artificial Intelligence,
Seattle, WA, USA, July 31 - August 4, 1994, Volume 1},
pages = {700--705},
publisher = {{AAAI} Press / The {MIT} Press},
year = {1994},
url = {http://www.aaai.org/Library/AAAI/1994/aaai94-107.php},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/Singh94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SinghJJ94,
author = {Satinder P. Singh and
Tommi S. Jaakkola and
Michael I. Jordan},
editor = {William W. Cohen and
Haym Hirsh},
title = {Learning Without State-Estimation in Partially Observable Markovian
Decision Processes},
booktitle = {Machine Learning, Proceedings of the Eleventh International Conference,
Rutgers University, New Brunswick, NJ, USA, July 10-13, 1994},
pages = {284--292},
publisher = {Morgan Kaufmann},
year = {1994},
url = {https://doi.org/10.1016/b978-1-55860-335-6.50042-8},
doi = {10.1016/B978-1-55860-335-6.50042-8},
timestamp = {Mon, 24 Jun 2019 13:56:31 +0200},
biburl = {https://dblp.org/rec/conf/icml/SinghJJ94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/JaakkolaSJ94,
author = {Tommi S. Jaakkola and
Satinder Singh and
Michael I. Jordan},
editor = {Gerald Tesauro and
David S. Touretzky and
Todd K. Leen},
title = {Reinforcement Learning Algorithm for Partially Observable Markov Decision
Problems},
booktitle = {Advances in Neural Information Processing Systems 7, {[NIPS} Conference,
Denver, Colorado, USA, 1994]},
pages = {345--352},
publisher = {{MIT} Press},
year = {1994},
url = {http://papers.nips.cc/paper/951-reinforcement-learning-algorithm-for-partially-observable-markov-decision-problems},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/JaakkolaSJ94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SinghJJ94,
author = {Satinder Singh and
Tommi S. Jaakkola and
Michael I. Jordan},
editor = {Gerald Tesauro and
David S. Touretzky and
Todd K. Leen},
title = {Reinforcement Learning with Soft State Aggregation},
booktitle = {Advances in Neural Information Processing Systems 7, {[NIPS} Conference,
Denver, Colorado, USA, 1994]},
pages = {361--368},
publisher = {{MIT} Press},
year = {1994},
url = {http://papers.nips.cc/paper/981-reinforcement-learning-with-soft-state-aggregation},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/SinghJJ94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SinghBGC93,
author = {Satinder Singh and
Andrew G. Barto and
Roderic A. Grupen and
Christopher I. Connolly},
editor = {Jack D. Cowan and
Gerald Tesauro and
Joshua Alspector},
title = {Robust Reinforcement Learning in Motion Planning},
booktitle = {Advances in Neural Information Processing Systems 6, [7th {NIPS} Conference,
Denver, Colorado, USA, 1993]},
pages = {655--662},
publisher = {Morgan Kaufmann},
year = {1993},
url = {http://papers.nips.cc/paper/843-robust-reinforcement-learning-in-motion-planning},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/SinghBGC93.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/JaakkolaJS93,
author = {Tommi S. Jaakkola and
Michael I. Jordan and
Satinder Singh},
editor = {Jack D. Cowan and
Gerald Tesauro and
Joshua Alspector},
title = {Convergence of Stochastic Iterative Dynamic Programming Algorithms},
booktitle = {Advances in Neural Information Processing Systems 6, [7th {NIPS} Conference,
Denver, Colorado, USA, 1993]},
pages = {703--710},
publisher = {Morgan Kaufmann},
year = {1993},
url = {http://papers.nips.cc/paper/764-convergence-of-stochastic-iterative-dynamic-programming-algorithms},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/JaakkolaJS93.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/Singh92,
author = {Satinder Pal Singh},
title = {Transfer of Learning by Composing Solutions of Elemental Sequential
Tasks},
journal = {Mach. Learn.},
volume = {8},
pages = {323--339},
year = {1992},
url = {https://doi.org/10.1007/BF00992700},
doi = {10.1007/BF00992700},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/Singh92.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/Singh92,
author = {Satinder P. Singh},
editor = {William R. Swartout},
title = {Reinforcement Learning with a Hierarchy of Abstract Models},
booktitle = {Proceedings of the 10th National Conference on Artificial Intelligence,
San Jose, CA, USA, July 12-16, 1992},
pages = {202--207},
publisher = {{AAAI} Press / The {MIT} Press},
year = {1992},
url = {http://www.aaai.org/Library/AAAI/1992/aaai92-032.php},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/Singh92.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/Singh92,
author = {Satinder P. Singh},
editor = {Derek H. Sleeman and
Peter Edwards},
title = {Scaling Reinforcement Learning Algorithms by Learning Variable Temporal
Resolution Models},
booktitle = {Proceedings of the Ninth International Workshop on Machine Learning
{(ML} 1992), Aberdeen, Scotland, UK, July 1-3, 1992},
pages = {406--415},
publisher = {Morgan Kaufmann},
year = {1992},
url = {https://doi.org/10.1016/b978-1-55860-247-2.50058-9},
doi = {10.1016/B978-1-55860-247-2.50058-9},
timestamp = {Fri, 21 Jun 2019 11:43:03 +0200},
biburl = {https://dblp.org/rec/conf/icml/Singh92.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/Singh91,
author = {Satinder P. Singh},
editor = {Lawrence Birnbaum and
Gregg Collins},
title = {Transfer of Learning Across Compositions of Sequentail Tasks},
booktitle = {Proceedings of the Eighth International Workshop (ML91), Northwestern
University, Evanston, Illinois, {USA}},
pages = {348--352},
publisher = {Morgan Kaufmann},
year = {1991},
url = {https://doi.org/10.1016/b978-1-55860-200-7.50072-6},
doi = {10.1016/B978-1-55860-200-7.50072-6},
timestamp = {Wed, 19 Jun 2019 17:09:09 +0200},
biburl = {https://dblp.org/rec/conf/icml/Singh91.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Singh91,
author = {Satinder Singh},
editor = {John E. Moody and
Stephen Jose Hanson and
Richard Lippmann},
title = {The Efficient Learning of Multiple Task Sequences},
booktitle = {Advances in Neural Information Processing Systems 4, {[NIPS} Conference,
Denver, Colorado, USA, December 2-5, 1991]},
pages = {251--258},
publisher = {Morgan Kaufmann},
year = {1991},
url = {http://papers.nips.cc/paper/569-the-efficient-learning-of-multiple-task-sequences},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/Singh91.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BerthierSBH91,
author = {N. E. Berthier and
Satinder P. Singh and
Andrew G. Barto and
James C. Houk},
editor = {John E. Moody and
Stephen Jose Hanson and
Richard Lippmann},
title = {A Cortico-Cerebellar Model that Learns to Generate Distributed Motor
Commands to Control a Kinematic Arm},
booktitle = {Advances in Neural Information Processing Systems 4, {[NIPS} Conference,
Denver, Colorado, USA, December 2-5, 1991]},
pages = {611--618},
publisher = {Morgan Kaufmann},
year = {1991},
url = {http://papers.nips.cc/paper/532-a-cortico-cerebellar-model-that-learns-to-generate-distributed-motor-commands-to-control-a-kinematic-arm},
timestamp = {Fri, 06 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/BerthierSBH91.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-04-21 17:30 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
