Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Martha White
@inproceedings{DBLP:conf/aaai/LiuWW24,
author = {Vincent Liu and
James R. Wright and
Martha White},
editor = {Michael J. Wooldridge and
Jennifer G. Dy and
Sriraam Natarajan},
title = {Exploiting Action Impact Regularity and Exogenous State Variables
for Offline Reinforcement Learning (Abstract Reprint)},
booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}
2024, Thirty-Sixth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,
Canada},
pages = {22706},
publisher = {{AAAI} Press},
year = {2024},
url = {https://doi.org/10.1609/aaai.v38i20.30606},
doi = {10.1609/AAAI.V38I20.30606},
timestamp = {Tue, 02 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/LiuWW24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-03903,
author = {Brett Daley and
Martha White and
Marlos C. Machado},
title = {Compound Returns Reduce Variance in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2402.03903},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.03903},
doi = {10.48550/ARXIV.2402.03903},
eprinttype = {arXiv},
eprint = {2402.03903},
timestamp = {Mon, 12 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-03903.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-10339,
author = {Hugo Silva and
Martha White},
title = {What to Do When Your Discrete Optimization Is the Size of a Neural
Network?},
journal = {CoRR},
volume = {abs/2402.10339},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.10339},
doi = {10.48550/ARXIV.2402.10339},
eprinttype = {arXiv},
eprint = {2402.10339},
timestamp = {Mon, 26 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-10339.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-13425,
author = {Ehsan Imani and
Kai Luedemann and
Sam Scholnick{-}Hughes and
Esraa Elelimy and
Martha White},
title = {Investigating the Histogram Loss in Regression},
journal = {CoRR},
volume = {abs/2402.13425},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.13425},
doi = {10.48550/ARXIV.2402.13425},
eprinttype = {arXiv},
eprint = {2402.13425},
timestamp = {Thu, 21 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-13425.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/LiuWW23,
author = {Vincent Liu and
James R. Wright and
Martha White},
title = {Exploiting Action Impact Regularity and Exogenous State Variables
for Offline Reinforcement Learning},
journal = {J. Artif. Intell. Res.},
volume = {77},
pages = {71--101},
year = {2023},
url = {https://doi.org/10.1613/jair.1.14580},
doi = {10.1613/JAIR.1.14580},
timestamp = {Mon, 22 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jair/LiuWW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/0002IKW23,
author = {Eric Graves and
Ehsan Imani and
Raksha Kumaraswamy and
Martha White},
title = {Off-Policy Actor-Critic with Emphatic Weightings},
journal = {J. Mach. Learn. Res.},
volume = {24},
pages = {146:1--146:63},
year = {2023},
url = {http://jmlr.org/papers/v24/21-1350.html},
timestamp = {Tue, 13 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/0002IKW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/JavedSSW23,
author = {Khurram Javed and
Haseeb Shah and
Richard S. Sutton and
Martha White},
title = {Scalable Real-Time Recurrent Learning Using Columnar-Constructive
Networks},
journal = {J. Mach. Learn. Res.},
volume = {24},
pages = {256:1--256:34},
year = {2023},
url = {http://jmlr.org/papers/v24/23-0367.html},
timestamp = {Thu, 19 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/JavedSSW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/PattersonLW23,
author = {Andrew Patterson and
Victor Liao and
Martha White},
title = {Robust Losses for Learning Value Functions},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {45},
number = {5},
pages = {6157--6167},
year = {2023},
url = {https://doi.org/10.1109/TPAMI.2022.3213503},
doi = {10.1109/TPAMI.2022.3213503},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pami/PattersonLW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmlr/SchlegelTWW23,
author = {Matthew Schlegel and
Volodymyr Tkachuk and
Adam M. White and
Martha White},
title = {Investigating Action Encodings in Recurrent Neural Networks in Reinforcement
Learning},
journal = {Trans. Mach. Learn. Res.},
volume = {2023},
year = {2023},
url = {https://openreview.net/forum?id=K6g4MbAC1r},
timestamp = {Thu, 18 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tmlr/SchlegelTWW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/LiuCTW23,
author = {Vincent Liu and
Yash Chandak and
Philip S. Thomas and
Martha White},
editor = {Francisco J. R. Ruiz and
Jennifer G. Dy and
Jan{-}Willem van de Meent},
title = {Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing
Old Data in Nonstationary Environments},
booktitle = {International Conference on Artificial Intelligence and Statistics,
25-27 April 2023, Palau de Congressos, Valencia, Spain},
series = {Proceedings of Machine Learning Research},
volume = {206},
pages = {5474--5492},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v206/liu23d.html},
timestamp = {Mon, 19 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/LiuCTW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/collas/LiuWTJ0W23,
author = {Vincent Liu and
Han Wang and
Ruo Yu Tao and
Khurram Javed and
Adam White and
Martha White},
editor = {Sarath Chandar and
Razvan Pascanu and
Hanie Sedghi and
Doina Precup},
title = {Measuring and Mitigating Interference in Reinforcement Learning},
booktitle = {Conference on Lifelong Learning Agents, 22-25 August 2023, McGill
University, Montr{\'{e}}al, Qu{\'{e}}bec, Canada},
series = {Proceedings of Machine Learning Research},
volume = {232},
pages = {781--795},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v232/liu23a.html},
timestamp = {Tue, 20 Feb 2024 13:52:18 +0100},
biburl = {https://dblp.org/rec/conf/collas/LiuWTJ0W23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/NeumannLJP0W23,
author = {Samuel Neumann and
Sungsu Lim and
Ajin George Joseph and
Yangchen Pan and
Adam White and
Martha White},
title = {Greedy Actor-Critic: {A} New Conditional Cross-Entropy Method for
Policy Improvement},
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=eSQh8rG8Oa},
timestamp = {Fri, 30 Jun 2023 14:38:38 +0200},
biburl = {https://dblp.org/rec/conf/iclr/NeumannLJP0W23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/XiaoWP0W23,
author = {Chenjun Xiao and
Han Wang and
Yangchen Pan and
Adam White and
Martha White},
title = {The In-Sample Softmax for Offline Reinforcement Learning},
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=u-RuvyDYqCM},
timestamp = {Fri, 30 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/XiaoWP0W23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/DaleyWAM23,
author = {Brett Daley and
Martha White and
Christopher Amato and
Marlos C. Machado},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {6818--6835},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/daley23a.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/DaleyWAM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZhuCSW23,
author = {Lingwei Zhu and
Zheng Chen and
Matthew Schlegel and
Martha White},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {General Munchausen Reinforcement Learning with Tsallis Kullback-Leibler
Divergence},
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/b3e866c228f8f4ea18021ae63aea5453-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ZhuCSW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-11321,
author = {Brett Daley and
Martha White and
Christopher Amato and
Marlos C. Machado},
title = {Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning},
journal = {CoRR},
volume = {abs/2301.11321},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.11321},
doi = {10.48550/ARXIV.2301.11321},
eprinttype = {arXiv},
eprint = {2301.11321},
timestamp = {Tue, 31 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-11321.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-11476,
author = {Lingwei Zhu and
Zheng Chen and
Takamitsu Matsubara and
Martha White},
title = {Generalized Munchausen Reinforcement Learning using Tsallis {KL} Divergence},
journal = {CoRR},
volume = {abs/2301.11476},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.11476},
doi = {10.48550/ARXIV.2301.11476},
eprinttype = {arXiv},
eprint = {2301.11476},
timestamp = {Tue, 31 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-11476.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-05326,
author = {Khurram Javed and
Haseeb Shah and
Richard S. Sutton and
Martha White},
title = {Online Real-Time Recurrent Learning Using Sparse Connections and Selective
Learning},
journal = {CoRR},
volume = {abs/2302.05326},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.05326},
doi = {10.48550/ARXIV.2302.05326},
eprinttype = {arXiv},
eprint = {2302.05326},
timestamp = {Mon, 13 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-05326.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-11725,
author = {Vincent Liu and
Yash Chandak and
Philip S. Thomas and
Martha White},
title = {Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing
Old Data in Nonstationary Environments},
journal = {CoRR},
volume = {abs/2302.11725},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.11725},
doi = {10.48550/ARXIV.2302.11725},
eprinttype = {arXiv},
eprint = {2302.11725},
timestamp = {Tue, 28 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-11725.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-14372,
author = {Chenjun Xiao and
Han Wang and
Yangchen Pan and
Adam White and
Martha White},
title = {The In-Sample Softmax for Offline Reinforcement Learning},
journal = {CoRR},
volume = {abs/2302.14372},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.14372},
doi = {10.48550/ARXIV.2302.14372},
eprinttype = {arXiv},
eprint = {2302.14372},
timestamp = {Thu, 02 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-14372.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2304-01315,
author = {Andrew Patterson and
Samuel Neumann and
Martha White and
Adam White},
title = {Empirical Design in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2304.01315},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2304.01315},
doi = {10.48550/ARXIV.2304.01315},
eprinttype = {arXiv},
eprint = {2304.01315},
timestamp = {Tue, 18 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2304-01315.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-09838,
author = {James E. Kostas and
Scott M. Jordan and
Yash Chandak and
Georgios Theocharous and
Dhawal Gupta and
Martha White and
Bruno Castro da Silva and
Philip S. Thomas},
title = {Coagent Networks: Generalized and Scaled},
journal = {CoRR},
volume = {abs/2305.09838},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.09838},
doi = {10.48550/ARXIV.2305.09838},
eprinttype = {arXiv},
eprint = {2305.09838},
timestamp = {Wed, 24 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-09838.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-04887,
author = {Vincent Liu and
Han Wang and
Ruo Yu Tao and
Khurram Javed and
Adam White and
Martha White},
title = {Measuring and Mitigating Interference in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2307.04887},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.04887},
doi = {10.48550/ARXIV.2307.04887},
eprinttype = {arXiv},
eprint = {2307.04887},
timestamp = {Mon, 24 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-04887.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-01624,
author = {Muhammad Kamran Janjua and
Haseeb Shah and
Martha White and
Erfan Miahi and
Marlos C. Machado and
Adam White},
title = {GVFs in the Real World: Making Predictions Online for Water Treatment},
journal = {CoRR},
volume = {abs/2312.01624},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.01624},
doi = {10.48550/ARXIV.2312.01624},
eprinttype = {arXiv},
eprint = {2312.01624},
timestamp = {Wed, 13 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-01624.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-02355,
author = {Vincent Liu and
Prabhat Nagarajan and
Andrew Patterson and
Martha White},
title = {When is Offline Policy Selection Sample Efficient for Reinforcement
Learning?},
journal = {CoRR},
volume = {abs/2312.02355},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.02355},
doi = {10.48550/ARXIV.2312.02355},
eprinttype = {arXiv},
eprint = {2312.02355},
timestamp = {Wed, 13 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-02355.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/Patterson0W22,
author = {Andrew Patterson and
Adam White and
Martha White},
title = {A Generalized Projected Bellman Error for Off-policy Value Estimation
in Reinforcement Learning},
journal = {J. Mach. Learn. Res.},
volume = {23},
pages = {145:1--145:61},
year = {2022},
url = {http://jmlr.org/papers/v23/21-037.html},
timestamp = {Wed, 07 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/Patterson0W22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/0001SLKMW22,
author = {Alan Chan and
Hugo Silva and
Sungsu Lim and
Tadashi Kozuno and
A. Rupam Mahmood and
Martha White},
title = {Greedification Operators for Policy Optimization: Investigating Forward
and Reverse {KL} Divergences},
journal = {J. Mach. Learn. Res.},
volume = {23},
pages = {253:1--253:79},
year = {2022},
url = {http://jmlr.org/papers/v23/21-054.html},
timestamp = {Wed, 07 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/0001SLKMW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmlr/ImaniHW22,
author = {Ehsan Imani and
Wei Hu and
Martha White},
title = {Representation Alignment in Neural Networks},
journal = {Trans. Mach. Learn. Res.},
volume = {2022},
year = {2022},
url = {https://openreview.net/forum?id=fLIWMnZ9ij},
timestamp = {Fri, 19 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tmlr/ImaniHW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmlr/WangSWBLZLKFW22,
author = {Han Wang and
Archit Sakhadeo and
Adam M. White and
James Bell and
Vincent Liu and
Xutong Zhao and
Puer Liu and
Tadashi Kozuno and
Alona Fyshe and
Martha White},
title = {No More Pesky Hyperparameters: Offline Hyperparameter Tuning for {RL}},
journal = {Trans. Mach. Learn. Res.},
volume = {2022},
year = {2022},
url = {https://openreview.net/forum?id=AiOUi3440V},
timestamp = {Fri, 19 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tmlr/WangSWBLZLKFW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/0006TPWM22,
author = {Shivam Garg and
Samuele Tosatto and
Yangchen Pan and
Martha White and
Rupam Mahmood},
editor = {Gustau Camps{-}Valls and
Francisco J. R. Ruiz and
Isabel Valera},
title = {An Alternate Policy Gradient Estimator for Softmax Policies},
booktitle = {International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2022, 28-30 March 2022, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {151},
pages = {6630--6689},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v151/garg22b.html},
timestamp = {Sat, 30 Sep 2023 09:34:08 +0200},
biburl = {https://dblp.org/rec/conf/aistats/0006TPWM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/BanmanP0FW22,
author = {Kirby Banman and
Liam Peet{-}Pare and
Nidhi Hegde and
Alona Fyshe and
Martha White},
title = {Resonance in Weight Space: Covariate Shift Can Drive Divergence of
{SGD} with Momentum},
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=5ECQL05ub0J},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/BanmanP0FW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/TosattoPWM22,
author = {Samuele Tosatto and
Andrew Patterson and
Martha White and
Rupam Mahmood},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {A Temporal-Difference Approach to Policy Gradient Estimation},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {21609--21632},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/tosatto22a.html},
timestamp = {Tue, 12 Jul 2022 17:36:52 +0200},
biburl = {https://dblp.org/rec/conf/icml/TosattoPWM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/PanMFWYR022,
author = {Yangchen Pan and
Jincheng Mei and
Amir{-}massoud Farahmand and
Martha White and
Hengshuai Yao and
Mohsen Rohani and
Jun Luo},
editor = {James Cussens and
Kun Zhang},
title = {Understanding and mitigating the limitations of prioritized experience
replay},
booktitle = {Uncertainty in Artificial Intelligence, Proceedings of the Thirty-Eighth
Conference on Uncertainty in Artificial Intelligence, {UAI} 2022,
1-5 August 2022, Eindhoven, The Netherlands},
series = {Proceedings of Machine Learning Research},
volume = {180},
pages = {1561--1571},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v180/pan22a.html},
timestamp = {Sat, 15 Oct 2022 12:08:13 +0200},
biburl = {https://dblp.org/rec/conf/uai/PanMFWYR022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-02396,
author = {Samuele Tosatto and
Andrew Patterson and
Martha White and
A. Rupam Mahmood},
title = {A Temporal-Difference Approach to Policy Gradient Estimation},
journal = {CoRR},
volume = {abs/2202.02396},
year = {2022},
url = {https://arxiv.org/abs/2202.02396},
eprinttype = {arXiv},
eprint = {2202.02396},
timestamp = {Wed, 09 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-02396.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-11133,
author = {Matthew McLeod and
Chunlok Lo and
Matthew Schlegel and
Andrew Jacobsen and
Raksha Kumaraswamy and
Martha White and
Adam White},
title = {Continual Auxiliary Task Learning},
journal = {CoRR},
volume = {abs/2202.11133},
year = {2022},
url = {https://arxiv.org/abs/2202.11133},
eprinttype = {arXiv},
eprint = {2202.11133},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-11133.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-11992,
author = {Kirby Banman and
Liam Peet{-}Pare and
Nidhi Hegde and
Alona Fyshe and
Martha White},
title = {Resonance in Weight Space: Covariate Shift Can Drive Divergence of
{SGD} with Momentum},
journal = {CoRR},
volume = {abs/2203.11992},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.11992},
doi = {10.48550/ARXIV.2203.11992},
eprinttype = {arXiv},
eprint = {2203.11992},
timestamp = {Tue, 29 Mar 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-11992.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-15955,
author = {Han Wang and
Erfan Miahi and
Martha White and
Marlos C. Machado and
Zaheer Abbas and
Raksha Kumaraswamy and
Vincent Liu and
Adam White},
title = {Investigating the Properties of Neural Network Representations in
Reinforcement Learning},
journal = {CoRR},
volume = {abs/2203.15955},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.15955},
doi = {10.48550/ARXIV.2203.15955},
eprinttype = {arXiv},
eprint = {2203.15955},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-15955.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-08464,
author = {Andrew Patterson and
Victor Liao and
Martha White},
title = {Robust Losses for Learning Value Functions},
journal = {CoRR},
volume = {abs/2205.08464},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.08464},
doi = {10.48550/ARXIV.2205.08464},
eprinttype = {arXiv},
eprint = {2205.08464},
timestamp = {Mon, 23 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-08464.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-08716,
author = {Han Wang and
Archit Sakhadeo and
Adam White and
James Bell and
Vincent Liu and
Xutong Zhao and
Puer Liu and
Tadashi Kozuno and
Alona Fyshe and
Martha White},
title = {No More Pesky Hyperparameters: Offline Hyperparameter Tuning for {RL}},
journal = {CoRR},
volume = {abs/2205.08716},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.08716},
doi = {10.48550/ARXIV.2205.08716},
eprinttype = {arXiv},
eprint = {2205.08716},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-08716.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-02902,
author = {Chunlok Lo and
Gabor Mihucz and
Adam White and
Farzane Aminmansour and
Martha White},
title = {Goal-Space Planning with Subgoal Models},
journal = {CoRR},
volume = {abs/2206.02902},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.02902},
doi = {10.48550/ARXIV.2206.02902},
eprinttype = {arXiv},
eprint = {2206.02902},
timestamp = {Tue, 14 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-02902.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/SchlegelJAPWW21,
author = {Matthew Schlegel and
Andrew Jacobsen and
Zaheer Abbas and
Andrew Patterson and
Adam White and
Martha White},
title = {General Value Function Networks},
journal = {J. Artif. Intell. Res.},
volume = {70},
pages = {497--543},
year = {2021},
url = {https://doi.org/10.1613/jair.1.12105},
doi = {10.1613/JAIR.1.12105},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jair/SchlegelJAPWW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tase/HoferBHGMGAFGLL21,
author = {Sebastian H{\"{o}}fer and
Kostas E. Bekris and
Ankur Handa and
Juan Camilo Gamboa and
Melissa Mozifian and
Florian Golemo and
Christopher G. Atkeson and
Dieter Fox and
Ken Goldberg and
John Leonard and
C. Karen Liu and
Jan Peters and
Shuran Song and
Peter Welinder and
Martha White},
title = {Sim2Real in Robotics and Automation: Applications and Challenges},
journal = {{IEEE} Trans Autom. Sci. Eng.},
volume = {18},
number = {2},
pages = {398--400},
year = {2021},
url = {https://doi.org/10.1109/TASE.2021.3064065},
doi = {10.1109/TASE.2021.3064065},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tase/HoferBHGMGAFGLL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/PanBW21,
author = {Yangchen Pan and
Kirby Banman and
Martha White},
title = {Fuzzy Tiling Activations: {A} Simple Approach to Learning Sparse Representations
Online},
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=zElset1Klrp},
timestamp = {Wed, 23 Jun 2021 17:36:39 +0200},
biburl = {https://dblp.org/rec/conf/iclr/PanBW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/McLeodLSJKWW21,
author = {Matthew McLeod and
Chunlok Lo and
Matthew Schlegel and
Andrew Jacobsen and
Raksha Kumaraswamy and
Martha White and
Adam White},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Continual Auxiliary Task Learning},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {12549--12562},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/68331ff0427b551b68e911eebe35233b-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/McLeodLSJKWW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GuptaMSKTW21,
author = {Dhawal Gupta and
Gabor Mihucz and
Matthew Schlegel and
James E. Kostas and
Philip S. Thomas and
Martha White},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Structural Credit Assignment in Neural Networks using Reinforcement
Learning},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {30257--30270},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/fe1f9c70bdf347497e1a01b6c486bdb9-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/GuptaMSKTW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-05787,
author = {Khurram Javed and
Martha White and
Richard S. Sutton},
title = {Scalable Online Recurrent Learning Using Columnar Neural Networks},
journal = {CoRR},
volume = {abs/2103.05787},
year = {2021},
url = {https://arxiv.org/abs/2103.05787},
eprinttype = {arXiv},
eprint = {2103.05787},
timestamp = {Tue, 16 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-05787.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-13844,
author = {Andrew Patterson and
Adam White and
Sina Ghiassian and
Martha White},
title = {A Generalized Projected Bellman Error for Off-policy Value Estimation
in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2104.13844},
year = {2021},
url = {https://arxiv.org/abs/2104.13844},
eprinttype = {arXiv},
eprint = {2104.13844},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-13844.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-14214,
author = {Qingfeng Lan and
Luke Kumar and
Martha White and
Alona Fyshe},
title = {Predictive Representation Learning for Language Modeling},
journal = {CoRR},
volume = {abs/2105.14214},
year = {2021},
url = {https://arxiv.org/abs/2105.14214},
eprinttype = {arXiv},
eprint = {2105.14214},
timestamp = {Wed, 02 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-14214.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-08285,
author = {Alan Chan and
Hugo Silva and
Sungsu Lim and
Tadashi Kozuno and
A. Rupam Mahmood and
Martha White},
title = {Greedification Operators for Policy Optimization: Investigating Forward
and Reverse {KL} Divergences},
journal = {CoRR},
volume = {abs/2107.08285},
year = {2021},
url = {https://arxiv.org/abs/2107.08285},
eprinttype = {arXiv},
eprint = {2107.08285},
timestamp = {Wed, 21 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-08285.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-08066,
author = {Vincent Liu and
James R. Wright and
Martha White},
title = {Exploiting Action Impact Regularity and Partially Known Models for
Offline Reinforcement Learning},
journal = {CoRR},
volume = {abs/2111.08066},
year = {2021},
url = {https://arxiv.org/abs/2111.08066},
eprinttype = {arXiv},
eprint = {2111.08066},
timestamp = {Mon, 22 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-08066.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-08172,
author = {Eric Graves and
Ehsan Imani and
Raksha Kumaraswamy and
Martha White},
title = {Off-Policy Actor-Critic with Emphatic Weightings},
journal = {CoRR},
volume = {abs/2111.08172},
year = {2021},
url = {https://arxiv.org/abs/2111.08172},
eprinttype = {arXiv},
eprint = {2111.08172},
timestamp = {Mon, 22 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-08172.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-07806,
author = {Ehsan Imani and
Wei Hu and
Martha White},
title = {Understanding Feature Transfer Through Representation Alignment},
journal = {CoRR},
volume = {abs/2112.07806},
year = {2021},
url = {https://arxiv.org/abs/2112.07806},
eprinttype = {arXiv},
eprint = {2112.07806},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-07806.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-11622,
author = {Shivam Garg and
Samuele Tosatto and
Yangchen Pan and
Martha White and
A. Rupam Mahmood},
title = {An Alternate Policy Gradient Estimator for Softmax Policies},
journal = {CoRR},
volume = {abs/2112.11622},
year = {2021},
url = {https://arxiv.org/abs/2112.11622},
eprinttype = {arXiv},
eprint = {2112.11622},
timestamp = {Tue, 04 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-11622.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/LinkeAWDW20,
author = {Cam Linke and
Nadia M. Ady and
Martha White and
Thomas Degris and
Adam White},
title = {Adapting Behavior via Intrinsic Reward: {A} Survey and Empirical Study},
journal = {J. Artif. Intell. Res.},
volume = {69},
pages = {1287--1332},
year = {2020},
url = {https://doi.org/10.1613/jair.1.12087},
doi = {10.1613/JAIR.1.12087},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jair/LinkeAWDW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SatsangiLWOW20,
author = {Yash Satsangi and
Sungsu Lim and
Shimon Whiteson and
Frans A. Oliehoek and
Martha White},
editor = {Amal El Fallah Seghrouchni and
Gita Sukthankar and
Bo An and
Neil Yorke{-}Smith},
title = {Maximizing Information Gain in Partially Observable Environments via
Prediction Rewards},
booktitle = {Proceedings of the 19th International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} '20, Auckland, New Zealand, May 9-13,
2020},
pages = {1215--1223},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
year = {2020},
url = {https://dl.acm.org/doi/10.5555/3398761.3398902},
doi = {10.5555/3398761.3398902},
timestamp = {Tue, 26 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/SatsangiLWOW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/HashemzadehKWMF20,
author = {Maryam Hashemzadeh and
Greta Kaufeld and
Martha White and
Andrea E. Martin and
Alona Fyshe},
editor = {Trevor Cohn and
Yulan He and
Yang Liu},
title = {From Language to Language-ish: How Brain-Like is an LSTM's Representation
of Atypical Language Stimuli?},
booktitle = {Findings of the Association for Computational Linguistics: {EMNLP}
2020, Online Event, 16-20 November 2020},
series = {Findings of {ACL}},
volume = {{EMNLP} 2020},
pages = {645--656},
publisher = {Association for Computational Linguistics},
year = {2020},
url = {https://doi.org/10.18653/v1/2020.findings-emnlp.57},
doi = {10.18653/V1/2020.FINDINGS-EMNLP.57},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/HashemzadehKWMF20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/LanPFW20,
author = {Qingfeng Lan and
Yangchen Pan and
Alona Fyshe and
Martha White},
title = {Maxmin Q-learning: Controlling the Estimation Bias of Q-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=Bkg0u3Etwr},
timestamp = {Thu, 07 May 2020 17:11:47 +0200},
biburl = {https://dblp.org/rec/conf/iclr/LanPFW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/NathLCLWW20,
author = {Somjit Nath and
Vincent Liu and
Alan Chan and
Xin Li and
Adam White and
Martha White},
title = {Training Recurrent Neural Networks Online by Learning Explicit State
Variables},
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=SJgmR0NKPr},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/NathLCLWW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AbbasSTW20,
author = {Zaheer Abbas and
Samuel Sokota and
Erin Talvitie and
Martha White},
title = {Selective Dyna-Style Planning Under Limited Model Capacity},
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 = {1--10},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/abbas20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/AbbasSTW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ChandakTSWMT20,
author = {Yash Chandak and
Georgios Theocharous and
Shiv Shankar and
Martha White and
Sridhar Mahadevan and
Philip S. Thomas},
title = {Optimizing for the Future in Non-Stationary MDPs},
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 = {1414--1425},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/chandak20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/ChandakTSWMT20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/GhiassianP0GWW20,
author = {Sina Ghiassian and
Andrew Patterson and
Shivam Garg and
Dhawal Gupta and
Adam White and
Martha White},
title = {Gradient Temporal-Difference Learning with Regularized Corrections},
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 = {3524--3534},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/ghiassian20a.html},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/GhiassianP0GWW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ChandakJTWT20,
author = {Yash Chandak and
Scott M. Jordan and
Georgios Theocharous and
Martha White and
Philip S. Thomas},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Towards Safe Policy Improvement for Non-Stationary MDPs},
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/680390c55bbd9ce416d1d69a9ab4760d-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ChandakJTWT20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/PanIFW20,
author = {Yangchen Pan and
Ehsan Imani and
Amir{-}massoud Farahmand and
Martha White},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {An implicit function learning approach for parametric modal regression},
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/83eaa6722798a773dd55e8fc7443aa09-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/PanIFW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-06195,
author = {Yangchen Pan and
Ehsan Imani and
Martha White and
Amir{-}massoud Farahmand},
title = {An implicit function learning approach for parametric modal regression},
journal = {CoRR},
volume = {abs/2002.06195},
year = {2020},
url = {https://arxiv.org/abs/2002.06195},
eprinttype = {arXiv},
eprint = {2002.06195},
timestamp = {Tue, 03 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-06195.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-06487,
author = {Qingfeng Lan and
Yangchen Pan and
Alona Fyshe and
Martha White},
title = {Maxmin Q-learning: Controlling the Estimation Bias of Q-learning},
journal = {CoRR},
volume = {abs/2002.06487},
year = {2020},
url = {https://arxiv.org/abs/2002.06487},
eprinttype = {arXiv},
eprint = {2002.06487},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-06487.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-04912,
author = {Yash Satsangi and
Sungsu Lim and
Shimon Whiteson and
Frans A. Oliehoek and
Martha White},
title = {Maximizing Information Gain in Partially Observable Environments via
Prediction Reward},
journal = {CoRR},
volume = {abs/2005.04912},
year = {2020},
url = {https://arxiv.org/abs/2005.04912},
eprinttype = {arXiv},
eprint = {2005.04912},
timestamp = {Thu, 14 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-04912.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-08158,
author = {Yash Chandak and
Georgios Theocharous and
Shiv Shankar and
Martha White and
Sridhar Mahadevan and
Philip S. Thomas},
title = {Optimizing for the Future in Non-Stationary MDPs},
journal = {CoRR},
volume = {abs/2005.08158},
year = {2020},
url = {https://arxiv.org/abs/2005.08158},
eprinttype = {arXiv},
eprint = {2005.08158},
timestamp = {Wed, 03 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-08158.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-04363,
author = {Taher Jafferjee and
Ehsan Imani and
Erin Talvitie and
Martha White and
Michael Bowling},
title = {Hallucinating Value: {A} Pitfall of Dyna-style Planning with Imperfect
Environment Models},
journal = {CoRR},
volume = {abs/2006.04363},
year = {2020},
url = {https://arxiv.org/abs/2006.04363},
eprinttype = {arXiv},
eprint = {2006.04363},
timestamp = {Fri, 12 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-04363.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-07461,
author = {Khurram Javed and
Martha White and
Yoshua Bengio},
title = {Learning Causal Models Online},
journal = {CoRR},
volume = {abs/2006.07461},
year = {2020},
url = {https://arxiv.org/abs/2006.07461},
eprinttype = {arXiv},
eprint = {2006.07461},
timestamp = {Wed, 17 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-07461.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-00611,
author = {Sina Ghiassian and
Andrew Patterson and
Shivam Garg and
Dhawal Gupta and
Adam White and
Martha White},
title = {Gradient Temporal-Difference Learning with Regularized Corrections},
journal = {CoRR},
volume = {abs/2007.00611},
year = {2020},
url = {https://arxiv.org/abs/2007.00611},
eprinttype = {arXiv},
eprint = {2007.00611},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-00611.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-02418,
author = {Zaheer Abbas and
Samuel Sokota and
Erin J. Talvitie and
Martha White},
title = {Selective Dyna-style Planning Under Limited Model Capacity},
journal = {CoRR},
volume = {abs/2007.02418},
year = {2020},
url = {https://arxiv.org/abs/2007.02418},
eprinttype = {arXiv},
eprint = {2007.02418},
timestamp = {Mon, 03 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-02418.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-03807,
author = {Vincent Liu and
Adam White and
Hengshuai Yao and
Martha White},
title = {Towards a practical measure of interference for reinforcement learning},
journal = {CoRR},
volume = {abs/2007.03807},
year = {2020},
url = {https://arxiv.org/abs/2007.03807},
eprinttype = {arXiv},
eprint = {2007.03807},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-03807.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-09569,
author = {Jincheng Mei and
Yangchen Pan and
Martha White and
Amir{-}massoud Farahmand and
Hengshuai Yao},
title = {Beyond Prioritized Replay: Sampling States in Model-Based {RL} via
Simulated Priorities},
journal = {CoRR},
volume = {abs/2007.09569},
year = {2020},
url = {https://arxiv.org/abs/2007.09569},
eprinttype = {arXiv},
eprint = {2007.09569},
timestamp = {Tue, 28 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-09569.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-07435,
author = {Maryam Hashemzadeh and
Greta Kaufeld and
Martha White and
Andrea E. Martin and
Alona Fyshe},
title = {From Language to Language-ish: How Brain-Like is an LSTM's Representation
of Nonsensical Language Stimuli?},
journal = {CoRR},
volume = {abs/2010.07435},
year = {2020},
url = {https://arxiv.org/abs/2010.07435},
eprinttype = {arXiv},
eprint = {2010.07435},
timestamp = {Tue, 20 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-07435.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-12645,
author = {Yash Chandak and
Scott M. Jordan and
Georgios Theocharous and
Martha White and
Philip S. Thomas},
title = {Towards Safe Policy Improvement for Non-Stationary MDPs},
journal = {CoRR},
volume = {abs/2010.12645},
year = {2020},
url = {https://arxiv.org/abs/2010.12645},
eprinttype = {arXiv},
eprint = {2010.12645},
timestamp = {Mon, 02 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-12645.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-03806,
author = {Sebastian H{\"{o}}fer and
Kostas E. Bekris and
Ankur Handa and
Juan Camilo Gamboa Higuera and
Florian Golemo and
Melissa Mozifian and
Christopher G. Atkeson and
Dieter Fox and
Ken Goldberg and
John Leonard and
C. Karen Liu and
Jan Peters and
Shuran Song and
Peter Welinder and
Martha White},
title = {Perspectives on Sim2Real Transfer for Robotics: {A} Summary of the
{R:} {SS} 2020 Workshop},
journal = {CoRR},
volume = {abs/2012.03806},
year = {2020},
url = {https://arxiv.org/abs/2012.03806},
eprinttype = {arXiv},
eprint = {2012.03806},
timestamp = {Tue, 29 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-03806.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/JacobsenSLDWW19,
author = {Andrew Jacobsen and
Matthew Schlegel and
Cameron Linke and
Thomas Degris and
Adam White and
Martha White},
title = {Meta-Descent for Online, Continual Prediction},
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 = {3943--3950},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33013943},
doi = {10.1609/AAAI.V33I01.33013943},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/JacobsenSLDWW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/LiuKLW19,
author = {Vincent Liu and
Raksha Kumaraswamy and
Lei Le and
Martha White},
title = {The Utility of Sparse Representations for Control in Reinforcement
Learning},
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 = {4384--4391},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33014384},
doi = {10.1609/AAAI.V33I01.33014384},
timestamp = {Tue, 02 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaai/LiuKLW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/ChungNJW19,
author = {Wesley Chung and
Somjit Nath and
Ajin Joseph and
Martha White},
title = {Two-Timescale Networks for Nonlinear Value Function Approximation},
booktitle = {7th International Conference on Learning Representations, {ICLR} 2019,
New Orleans, LA, USA, May 6-9, 2019},
publisher = {OpenReview.net},
year = {2019},
url = {https://openreview.net/forum?id=rJleN20qK7},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/ChungNJW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/PanYFW19,
author = {Yangchen Pan and
Hengshuai Yao and
Amir{-}massoud Farahmand and
Martha White},
editor = {Sarit Kraus},
title = {Hill Climbing on Value Estimates for Search-control in Dyna},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16,
2019},
pages = {3209--3215},
publisher = {ijcai.org},
year = {2019},
url = {https://doi.org/10.24963/ijcai.2019/445},
doi = {10.24963/IJCAI.2019/445},
timestamp = {Tue, 20 Aug 2019 16:18:18 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/PanYFW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/WanZWWS19,
author = {Yi Wan and
Muhammad Zaheer and
Adam White and
Martha White and
Richard S. Sutton},
editor = {Sarit Kraus},
title = {Planning with Expectation Models},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16,
2019},
pages = {3649--3655},
publisher = {ijcai.org},
year = {2019},
url = {https://doi.org/10.24963/ijcai.2019/506},
doi = {10.24963/IJCAI.2019/506},
timestamp = {Thu, 14 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ijcai/WanZWWS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SchlegelCGQW19,
author = {Matthew Schlegel and
Wesley Chung and
Daniel Graves and
Jian Qian and
Martha White},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Importance Resampling for Off-policy Prediction},
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 = {1797--1807},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/9ac403da7947a183884c18a67d3aa8de-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/SchlegelCGQW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/JavedW19,
author = {Khurram Javed and
Martha White},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Meta-Learning Representations for Continual Learning},
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 = {1818--1828},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/f4dd765c12f2ef67f98f3558c282a9cd-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/JavedW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AminmansourPLPM19,
author = {Farzane Aminmansour and
Andrew Patterson and
Lei Le and
Yisu Peng and
Daniel Mitchell and
Franco Pestilli and
Cesar F. Caiafa and
Russell Greiner and
Martha White},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Learning Macroscopic Brain Connectomes via Group-Sparse Factorization},
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 = {8847--8857},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/0bfce127947574733b19da0f30739fcd-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/AminmansourPLPM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-01191,
author = {Yi Wan and
Muhammad Zaheer and
Adam White and
Martha White and
Richard S. Sutton},
title = {Planning with Expectation Models},
journal = {CoRR},
volume = {abs/1904.01191},
year = {2019},
url = {http://arxiv.org/abs/1904.01191},
eprinttype = {arXiv},
eprint = {1904.01191},
timestamp = {Thu, 14 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-01191.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-12588,
author = {Khurram Javed and
Martha White},
title = {Meta-Learning Representations for Continual Learning},
journal = {CoRR},
volume = {abs/1905.12588},
year = {2019},
url = {http://arxiv.org/abs/1905.12588},
eprinttype = {arXiv},
eprint = {1905.12588},
timestamp = {Mon, 03 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-12588.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-04328,
author = {Matthew Schlegel and
Wesley Chung and
Daniel Graves and
Jian Qian and
Martha White},
title = {Importance Resampling for Off-policy Prediction},
journal = {CoRR},
volume = {abs/1906.04328},
year = {2019},
url = {http://arxiv.org/abs/1906.04328},
eprinttype = {arXiv},
eprint = {1906.04328},
timestamp = {Fri, 14 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-04328.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-07791,
author = {Yangchen Pan and
Hengshuai Yao and
Amir{-}massoud Farahmand and
Martha White},
title = {Hill Climbing on Value Estimates for Search-control in Dyna},
journal = {CoRR},
volume = {abs/1906.07791},
year = {2019},
url = {http://arxiv.org/abs/1906.07791},
eprinttype = {arXiv},
eprint = {1906.07791},
timestamp = {Mon, 24 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-07791.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-07865,
author = {Cam Linke and
Nadia M. Ady and
Martha White and
Thomas Degris and
Adam White},
title = {Adapting Behaviour via Intrinsic Reward: {A} Survey and Empirical
Study},
journal = {CoRR},
volume = {abs/1906.07865},
year = {2019},
url = {http://arxiv.org/abs/1906.07865},
eprinttype = {arXiv},
eprint = {1906.07865},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-07865.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-07751,
author = {Andrew Jacobsen and
Matthew Schlegel and
Cameron Linke and
Thomas Degris and
Adam White and
Martha White},
title = {Meta-descent for Online, Continual Prediction},
journal = {CoRR},
volume = {abs/1907.07751},
year = {2019},
url = {http://arxiv.org/abs/1907.07751},
eprinttype = {arXiv},
eprint = {1907.07751},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-07751.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-01705,
author = {Khurram Javed and
Hengshuai Yao and
Martha White},
title = {Is Fast Adaptation All You Need?},
journal = {CoRR},
volume = {abs/1910.01705},
year = {2019},
url = {http://arxiv.org/abs/1910.01705},
eprinttype = {arXiv},
eprint = {1910.01705},
timestamp = {Wed, 09 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-01705.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ImaniW18,
author = {Ehsan Imani and
Martha White},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Improving Regression Performance with Distributional Losses},
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 = {2162--2171},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/imani18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:30 +0200},
biburl = {https://dblp.org/rec/conf/icml/ImaniW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/PanFWNGN18,
author = {Yangchen Pan and
Amir{-}massoud Farahmand and
Martha White and
Saleh Nabi and
Piyush Grover and
Daniel Nikovski},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Reinforcement Learning with Function-Valued Action Spaces for Partial
Differential Equation Control},
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 = {3983--3992},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/pan18a.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/PanFWNGN18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/PanZWPW18,
author = {Yangchen Pan and
Muhammad Zaheer and
Adam White and
Andrew Patterson and
Martha White},
editor = {J{\'{e}}r{\^{o}}me Lang},
title = {Organizing Experience: a Deeper Look at Replay Mechanisms for Sample-Based
Planning in Continuous State Domains},
booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on
Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm,
Sweden},
pages = {4794--4800},
publisher = {ijcai.org},
year = {2018},
url = {https://doi.org/10.24963/ijcai.2018/666},
doi = {10.24963/IJCAI.2018/666},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/PanZWPW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ImaniGW18,
author = {Ehsan Imani and
Eric Graves and
Martha White},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
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 = {96--106},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/3ef815416f775098fe977004015c6193-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/ImaniGW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LePW18,
author = {Lei Le and
Andrew Patterson and
Martha White},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {Supervised autoencoders: Improving generalization performance with
unsupervised regularizers},
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 = {107--117},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/2a38a4a9316c49e5a833517c45d31070-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/LePW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KumaraswamySWW18,
author = {Raksha Kumaraswamy and
Matthew Schlegel and
Adam White and
Martha White},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {Context-dependent upper-confidence bounds for directed exploration},
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 = {4784--4794},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/f516dfb84b9051ed85b89cdc3a8ab7f5-Abstract.html},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/KumaraswamySWW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/SherstanABYWWS18,
author = {Craig Sherstan and
Dylan R. Ashley and
Brendan Bennett and
Kenny Young and
Adam White and
Martha White and
Richard S. Sutton},
editor = {Amir Globerson and
Ricardo Silva},
title = {Comparing Direct and Indirect Temporal-Difference Methods for Estimating
the Variance of the Return},
booktitle = {Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial
Intelligence, {UAI} 2018, Monterey, California, USA, August 6-10,
2018},
pages = {63--72},
publisher = {{AUAI} Press},
year = {2018},
url = {http://auai.org/uai2018/proceedings/papers/35.pdf},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/SherstanABYWWS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/SajedCW18,
author = {Touqir Sajed and
Wesley Chung and
Martha White},
editor = {Amir Globerson and
Ricardo Silva},
title = {High-confidence error estimates for learned value functions},
booktitle = {Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial
Intelligence, {UAI} 2018, Monterey, California, USA, August 6-10,
2018},
pages = {683--692},
publisher = {{AUAI} Press},
year = {2018},
url = {http://auai.org/uai2018/proceedings/papers/245.pdf},
timestamp = {Wed, 09 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/uai/SajedCW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-08287,
author = {Craig Sherstan and
Brendan Bennett and
Kenny Young and
Dylan R. Ashley and
Adam White and
Martha White and
Richard S. Sutton},
title = {Directly Estimating the Variance of the {\(\lambda\)}-Return Using
Temporal-Difference Methods},
journal = {CoRR},
volume = {abs/1801.08287},
year = {2018},
url = {http://arxiv.org/abs/1801.08287},
eprinttype = {arXiv},
eprint = {1801.08287},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1801-08287.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-04613,
author = {Ehsan Imani and
Martha White},
title = {Improving Regression Performance with Distributional Losses},
journal = {CoRR},
volume = {abs/1806.04613},
year = {2018},
url = {http://arxiv.org/abs/1806.04613},
eprinttype = {arXiv},
eprint = {1806.04613},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-04613.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-04624,
author = {Yangchen Pan and
Muhammad Zaheer and
Adam White and
Andrew Patterson and
Martha White},
title = {Organizing Experience: {A} Deeper Look at Replay Mechanisms for Sample-based
Planning in Continuous State Domains},
journal = {CoRR},
volume = {abs/1806.04624},
year = {2018},
url = {http://arxiv.org/abs/1806.04624},
eprinttype = {arXiv},
eprint = {1806.04624},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-04624.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-06931,
author = {Yangchen Pan and
Amir{-}massoud Farahmand and
Martha White and
Saleh Nabi and
Piyush Grover and
Daniel Nikovski},
title = {Reinforcement Learning with Function-Valued Action Spaces for Partial
Differential Equation Control},
journal = {CoRR},
volume = {abs/1806.06931},
year = {2018},
url = {http://arxiv.org/abs/1806.06931},
eprinttype = {arXiv},
eprint = {1806.06931},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-06931.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1807-06763,
author = {Matthew Schlegel and
Adam White and
Andrew Patterson and
Martha White},
title = {General Value Function Networks},
journal = {CoRR},
volume = {abs/1807.06763},
year = {2018},
url = {http://arxiv.org/abs/1807.06763},
eprinttype = {arXiv},
eprint = {1807.06763},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1807-06763.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1808-09127,
author = {Touqir Sajed and
Wesley Chung and
Martha White},
title = {High-confidence error estimates for learned value functions},
journal = {CoRR},
volume = {abs/1808.09127},
year = {2018},
url = {http://arxiv.org/abs/1808.09127},
eprinttype = {arXiv},
eprint = {1808.09127},
timestamp = {Mon, 03 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1808-09127.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-09103,
author = {Sungsu Lim and
Ajin Joseph and
Lei Le and
Yangchen Pan and
Martha White},
title = {Actor-Expert: {A} Framework for using Action-Value Methods in Continuous
Action Spaces},
journal = {CoRR},
volume = {abs/1810.09103},
year = {2018},
url = {http://arxiv.org/abs/1810.09103},
eprinttype = {arXiv},
eprint = {1810.09103},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-09103.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-02597,
author = {Sina Ghiassian and
Andrew Patterson and
Martha White and
Richard S. Sutton and
Adam White},
title = {Online Off-policy Prediction},
journal = {CoRR},
volume = {abs/1811.02597},
year = {2018},
url = {http://arxiv.org/abs/1811.02597},
eprinttype = {arXiv},
eprint = {1811.02597},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-02597.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-06626,
author = {Vincent Liu and
Raksha Kumaraswamy and
Lei Le and
Martha White},
title = {The Utility of Sparse Representations for Control in Reinforcement
Learning},
journal = {CoRR},
volume = {abs/1811.06626},
year = {2018},
url = {http://arxiv.org/abs/1811.06626},
eprinttype = {arXiv},
eprint = {1811.06626},
timestamp = {Sun, 25 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-06626.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-06629,
author = {Raksha Kumaraswamy and
Matthew Schlegel and
Adam White and
Martha White},
title = {Context-Dependent Upper-Confidence Bounds for Directed Exploration},
journal = {CoRR},
volume = {abs/1811.06629},
year = {2018},
url = {http://arxiv.org/abs/1811.06629},
eprinttype = {arXiv},
eprint = {1811.06629},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-06629.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-07004,
author = {Tom Schaul and
Hado van Hasselt and
Joseph Modayil and
Martha White and
Adam White and
Pierre{-}Luc Bacon and
Jean Harb and
Shibl Mourad and
Marc G. Bellemare and
Doina Precup},
title = {The Barbados 2018 List of Open Issues in Continual Learning},
journal = {CoRR},
volume = {abs/1811.07004},
year = {2018},
url = {http://arxiv.org/abs/1811.07004},
eprinttype = {arXiv},
eprint = {1811.07004},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-07004.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-09013,
author = {Ehsan Imani and
Eric Graves and
Martha White},
title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
journal = {CoRR},
volume = {abs/1811.09013},
year = {2018},
url = {http://arxiv.org/abs/1811.09013},
eprinttype = {arXiv},
eprint = {1811.09013},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-09013.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-00914,
author = {Minghan Li and
Tanli Zuo and
Ruicheng Li and
Martha White and
Weishi Zheng},
title = {Accelerating Large Scale Knowledge Distillation via Dynamic Importance
Sampling},
journal = {CoRR},
volume = {abs/1812.00914},
year = {2018},
url = {http://arxiv.org/abs/1812.00914},
eprinttype = {arXiv},
eprint = {1812.00914},
timestamp = {Tue, 19 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-00914.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/JainWR17,
author = {Shantanu Jain and
Martha White and
Predrag Radivojac},
editor = {Satinder Singh and
Shaul Markovitch},
title = {Recovering True Classifier Performance in Positive-Unlabeled Learning},
booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence,
February 4-9, 2017, San Francisco, California, {USA}},
pages = {2066--2072},
publisher = {{AAAI} Press},
year = {2017},
url = {https://doi.org/10.1609/aaai.v31i1.10937},
doi = {10.1609/AAAI.V31I1.10937},
timestamp = {Mon, 04 Sep 2023 14:40:32 +0200},
biburl = {https://dblp.org/rec/conf/aaai/JainWR17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/PanWW17,
author = {Yangchen Pan and
Adam White and
Martha White},
editor = {Satinder Singh and
Shaul Markovitch},
title = {Accelerated Gradient Temporal Difference Learning},
booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence,
February 4-9, 2017, San Francisco, California, {USA}},
pages = {2464--2470},
publisher = {{AAAI} Press},
year = {2017},
url = {https://doi.org/10.1609/aaai.v31i1.10829},
doi = {10.1609/AAAI.V31I1.10829},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/PanWW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SchlegelPCW17,
author = {Matthew Schlegel and
Yangchen Pan and
Jiecao Chen and
Martha White},
editor = {Doina Precup and
Yee Whye Teh},
title = {Adapting Kernel Representations Online Using Submodular Maximization},
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 = {3037--3046},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/schlegel17a.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/SchlegelPCW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/White17,
author = {Martha White},
editor = {Doina Precup and
Yee Whye Teh},
title = {Unifying Task Specification in 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 = {3742--3750},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/white17a.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/White17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/LeKW17,
author = {Lei Le and
Raksha Kumaraswamy and
Martha White},
editor = {Carles Sierra},
title = {Learning Sparse Representations in Reinforcement Learning with Sparse
Coding},
booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on
Artificial Intelligence, {IJCAI} 2017, Melbourne, Australia, August
19-25, 2017},
pages = {2067--2073},
publisher = {ijcai.org},
year = {2017},
url = {https://doi.org/10.24963/ijcai.2017/287},
doi = {10.24963/IJCAI.2017/287},
timestamp = {Tue, 20 Aug 2019 16:16:54 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/LeKW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KaramiWSS17,
author = {Mahdi Karami and
Martha White and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
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 = {Multi-view Matrix Factorization for Linear Dynamical System Estimation},
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 = {7092--7101},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/c2964caac096f26db222cb325aa267cb-Abstract.html},
timestamp = {Thu, 21 Jan 2021 13:58:27 +0100},
biburl = {https://dblp.org/rec/conf/nips/KaramiWSS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/PanAW17,
author = {Yangchen Pan and
Erfan Sadeqi Azer and
Martha White},
editor = {Gal Elidan and
Kristian Kersting and
Alexander Ihler},
title = {Effective sketching methods for value function approximation},
booktitle = {Proceedings of the Thirty-Third Conference on Uncertainty in Artificial
Intelligence, {UAI} 2017, Sydney, Australia, August 11-15, 2017},
publisher = {{AUAI} Press},
year = {2017},
url = {http://auai.org/uai2017/proceedings/papers/81.pdf},
timestamp = {Mon, 05 Dec 2022 15:54:38 +0100},
biburl = {https://dblp.org/rec/conf/uai/PanAW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/JainWR17,
author = {Shantanu Jain and
Martha White and
Predrag Radivojac},
title = {Recovering True Classifier Performance in Positive-Unlabeled Learning},
journal = {CoRR},
volume = {abs/1702.00518},
year = {2017},
url = {http://arxiv.org/abs/1702.00518},
eprinttype = {arXiv},
eprint = {1702.00518},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/JainWR17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LeKW17,
author = {Lei Le and
Raksha Kumaraswamy and
Martha White},
title = {Learning Sparse Representations in Reinforcement Learning with Sparse
Coding},
journal = {CoRR},
volume = {abs/1707.08316},
year = {2017},
url = {http://arxiv.org/abs/1707.08316},
eprinttype = {arXiv},
eprint = {1707.08316},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LeKW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-01298,
author = {Yangchen Pan and
Erfan Sadeqi Azer and
Martha White},
title = {Effective sketching methods for value function approximation},
journal = {CoRR},
volume = {abs/1708.01298},
year = {2017},
url = {http://arxiv.org/abs/1708.01298},
eprinttype = {arXiv},
eprint = {1708.01298},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-01298.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/SuttonMW16,
author = {Richard S. Sutton and
Ashique Rupam Mahmood and
Martha White},
title = {An Emphatic Approach to the Problem of Off-policy Temporal-Difference
Learning},
journal = {J. Mach. Learn. Res.},
volume = {17},
pages = {73:1--73:29},
year = {2016},
url = {http://jmlr.org/papers/v17/14-488.html},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/SuttonMW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/AdamW16,
author = {Adam White and
Martha White},
editor = {Catholijn M. Jonker and
Stacy Marsella and
John Thangarajah and
Karl Tuyls},
title = {Investigating Practical Linear Temporal Difference Learning},
booktitle = {Proceedings of the 2016 International Conference on Autonomous Agents
{\&} Multiagent Systems, Singapore, May 9-13, 2016},
pages = {494--502},
publisher = {{ACM}},
year = {2016},
url = {http://dl.acm.org/citation.cfm?id=2936997},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/AdamW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/WhiteW16,
author = {Martha White and
Adam White},
editor = {Catholijn M. Jonker and
Stacy Marsella and
John Thangarajah and
Karl Tuyls},
title = {A Greedy Approach to Adapting the Trace Parameter for Temporal Difference
Learning},
booktitle = {Proceedings of the 2016 International Conference on Autonomous Agents
{\&} Multiagent Systems, Singapore, May 9-13, 2016},
pages = {557--565},
publisher = {{ACM}},
year = {2016},
url = {http://dl.acm.org/citation.cfm?id=2937006},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/WhiteW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/GehringPW16,
author = {Clement Gehring and
Yangchen Pan and
Martha White},
editor = {Subbarao Kambhampati},
title = {Incremental Truncated {LSTD}},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI} 2016, New York, NY, USA, 9-15 July
2016},
pages = {1505--1511},
publisher = {{IJCAI/AAAI} Press},
year = {2016},
url = {http://www.ijcai.org/Abstract/16/216},
timestamp = {Tue, 20 Aug 2019 16:19:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/GehringPW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/JainWR16,
author = {Shantanu Jain and
Martha White and
Predrag Radivojac},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {Estimating the class prior and posterior from noisy positives and
unlabeled data},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {2685--2693},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/79a49b3e3762632813f9e35f4ba53d6c-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/JainWR16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/JainWTR16,
author = {Shantanu Jain and
Martha White and
Michael W. Trosset and
Predrag Radivojac},
title = {Nonparametric semi-supervised learning of class proportions},
journal = {CoRR},
volume = {abs/1601.01944},
year = {2016},
url = {http://arxiv.org/abs/1601.01944},
eprinttype = {arXiv},
eprint = {1601.01944},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/JainWTR16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WhiteW16,
author = {Adam White and
Martha White},
title = {Investigating practical, linear temporal difference learning},
journal = {CoRR},
volume = {abs/1602.08771},
year = {2016},
url = {http://arxiv.org/abs/1602.08771},
eprinttype = {arXiv},
eprint = {1602.08771},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WhiteW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LeW16,
author = {Lei Le and
Martha White},
title = {Global optimization of factor models using alternating minimization},
journal = {CoRR},
volume = {abs/1604.04942},
year = {2016},
url = {http://arxiv.org/abs/1604.04942},
eprinttype = {arXiv},
eprint = {1604.04942},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LeW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/JainWR16,
author = {Shantanu Jain and
Martha White and
Predrag Radivojac},
title = {Estimating the class prior and posterior from noisy positives and
unlabeled data},
journal = {CoRR},
volume = {abs/1606.08561},
year = {2016},
url = {http://arxiv.org/abs/1606.08561},
eprinttype = {arXiv},
eprint = {1606.08561},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/JainWR16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WhiteW16a,
author = {Martha White and
Adam White},
title = {A Greedy Approach to Adapting the Trace Parameter for Temporal Difference
Learning},
journal = {CoRR},
volume = {abs/1607.00446},
year = {2016},
url = {http://arxiv.org/abs/1607.00446},
eprinttype = {arXiv},
eprint = {1607.00446},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WhiteW16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/White16,
author = {Martha White},
title = {Unifying task specification in reinforcement learning},
journal = {CoRR},
volume = {abs/1609.01995},
year = {2016},
url = {http://arxiv.org/abs/1609.01995},
eprinttype = {arXiv},
eprint = {1609.01995},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/White16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PanWW16,
author = {Yangchen Pan and
Adam White and
Martha White},
title = {Accelerated Gradient Temporal Difference Learning},
journal = {CoRR},
volume = {abs/1611.09328},
year = {2016},
url = {http://arxiv.org/abs/1611.09328},
eprinttype = {arXiv},
eprint = {1611.09328},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PanWW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/WhiteWBS15,
author = {Martha White and
Junfeng Wen and
Michael Bowling and
Dale Schuurmans},
editor = {Blai Bonet and
Sven Koenig},
title = {Optimal Estimation of Multivariate {ARMA} Models},
booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence,
January 25-30, 2015, Austin, Texas, {USA}},
pages = {3080--3086},
publisher = {{AAAI} Press},
year = {2015},
url = {https://doi.org/10.1609/aaai.v29i1.9614},
doi = {10.1609/AAAI.V29I1.9614},
timestamp = {Mon, 18 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/WhiteWBS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/MirzazadehWGS15,
author = {Farzaneh Mirzazadeh and
Martha White and
Andr{\'{a}}s Gy{\"{o}}rgy and
Dale Schuurmans},
editor = {Annalisa Appice and
Pedro Pereira Rodrigues and
V{\'{\i}}tor Santos Costa and
Carlos Soares and
Jo{\~{a}}o Gama and
Al{\'{\i}}pio Jorge},
title = {Scalable Metric Learning for Co-Embedding},
booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference,
{ECML} {PKDD} 2015, Porto, Portugal, September 7-11, 2015, Proceedings,
Part {I}},
series = {Lecture Notes in Computer Science},
volume = {9284},
pages = {625--642},
publisher = {Springer},
year = {2015},
url = {https://doi.org/10.1007/978-3-319-23528-8\_39},
doi = {10.1007/978-3-319-23528-8\_39},
timestamp = {Mon, 30 Nov 2020 08:47:26 +0100},
biburl = {https://dblp.org/rec/conf/pkdd/MirzazadehWGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SuttonMW15,
author = {Richard S. Sutton and
Ashique Rupam Mahmood and
Martha White},
title = {An Emphatic Approach to the Problem of Off-policy Temporal-Difference
Learning},
journal = {CoRR},
volume = {abs/1503.04269},
year = {2015},
url = {http://arxiv.org/abs/1503.04269},
eprinttype = {arXiv},
eprint = {1503.04269},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SuttonMW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MahmoodYWS15,
author = {Ashique Rupam Mahmood and
Huizhen Yu and
Martha White and
Richard S. Sutton},
title = {Emphatic Temporal-Difference Learning},
journal = {CoRR},
volume = {abs/1507.01569},
year = {2015},
url = {http://arxiv.org/abs/1507.01569},
eprinttype = {arXiv},
eprint = {1507.01569},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MahmoodYWS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/GehringW15,
author = {Clement Gehring and
Martha White},
title = {Incremental Truncated {LSTD}},
journal = {CoRR},
volume = {abs/1511.08495},
year = {2015},
url = {http://arxiv.org/abs/1511.08495},
eprinttype = {arXiv},
eprint = {1511.08495},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/GehringW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dcc/VenessWBG13,
author = {Joel Veness and
Martha White and
Michael Bowling and
Andr{\'{a}}s Gy{\"{o}}rgy},
editor = {Ali Bilgin and
Michael W. Marcellin and
Joan Serra{-}Sagrist{\`{a}} and
James A. Storer},
title = {Partition Tree Weighting},
booktitle = {2013 Data Compression Conference, {DCC} 2013, Snowbird, UT, USA, March
20-22, 2013},
pages = {321--330},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/DCC.2013.40},
doi = {10.1109/DCC.2013.40},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/dcc/VenessWBG13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/DegrisWS12,
author = {Thomas Degris and
Martha White and
Richard S. Sutton},
title = {Linear Off-Policy Actor-Critic},
booktitle = {Proceedings of the 29th International Conference on Machine Learning,
{ICML} 2012, Edinburgh, Scotland, UK, June 26 - July 1, 2012},
publisher = {icml.cc / Omnipress},
year = {2012},
url = {http://icml.cc/2012/papers/268.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/DegrisWS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WhiteYZS12,
author = {Martha White and
Yaoliang Yu and
Xinhua Zhang and
Dale Schuurmans},
editor = {Peter L. Bartlett and
Fernando C. N. Pereira and
Christopher J. C. Burges and
L{\'{e}}on Bottou and
Kilian Q. Weinberger},
title = {Convex Multi-view Subspace Learning},
booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual
Conference on Neural Information Processing Systems 2012. Proceedings
of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States},
pages = {1682--1690},
year = {2012},
url = {https://proceedings.neurips.cc/paper/2012/hash/1141938ba2c2b13f5505d7c424ebae5f-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/WhiteYZS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/WhiteS12,
author = {Martha White and
Dale Schuurmans},
editor = {Neil D. Lawrence and
Mark A. Girolami},
title = {Generalized Optimal Reverse Prediction},
booktitle = {Proceedings of the Fifteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2012, La Palma, Canary Islands,
Spain, April 21-23, 2012},
series = {{JMLR} Proceedings},
volume = {22},
pages = {1305--1313},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v22/white12.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/WhiteS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1205-4839,
author = {Thomas Degris and
Martha White and
Richard S. Sutton},
title = {Off-Policy Actor-Critic},
journal = {CoRR},
volume = {abs/1205.4839},
year = {2012},
url = {http://arxiv.org/abs/1205.4839},
eprinttype = {arXiv},
eprint = {1205.4839},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1205-4839.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1211-0587,
author = {Joel Veness and
Martha White and
Michael Bowling and
Andr{\'{a}}s Gy{\"{o}}rgy},
title = {Partition Tree Weighting},
journal = {CoRR},
volume = {abs/1211.0587},
year = {2012},
url = {http://arxiv.org/abs/1211.0587},
eprinttype = {arXiv},
eprint = {1211.0587},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1211-0587.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZhangYWHS11,
author = {Xinhua Zhang and
Yaoliang Yu and
Martha White and
Ruitong Huang and
Dale Schuurmans},
editor = {Wolfram Burgard and
Dan Roth},
title = {Convex Sparse Coding, Subspace Learning, and Semi-Supervised Extensions},
booktitle = {Proceedings of the Twenty-Fifth {AAAI} Conference on Artificial Intelligence,
{AAAI} 2011, San Francisco, California, USA, August 7-11, 2011},
pages = {567--573},
publisher = {{AAAI} Press},
year = {2011},
url = {https://doi.org/10.1609/aaai.v25i1.7935},
doi = {10.1609/AAAI.V25I1.7935},
timestamp = {Mon, 04 Sep 2023 16:05:54 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZhangYWHS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WhiteW10,
author = {Martha White and
Adam White},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Interval Estimation for Reinforcement-Learning Algorithms in Continuous-State
Domains},
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 = {2433--2441},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/13f3cf8c531952d72e5847c4183e6910-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/WhiteW10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/YuYXWS10,
author = {Yaoliang Yu and
Min Yang and
Linli Xu and
Martha White and
Dale Schuurmans},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Relaxed Clipping: {A} Global Training Method for Robust Regression
and Classification},
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 = {2532--2540},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/01882513d5fa7c329e940dda99b12147-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/YuYXWS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/XuWS09,
author = {Linli Xu and
Martha White and
Dale Schuurmans},
editor = {Andrea Pohoreckyj Danyluk and
L{\'{e}}on Bottou and
Michael L. Littman},
title = {Optimal reverse prediction: a unified perspective on supervised, unsupervised
and semi-supervised learning},
booktitle = {Proceedings of the 26th Annual International Conference on Machine
Learning, {ICML} 2009, Montreal, Quebec, Canada, June 14-18, 2009},
series = {{ACM} International Conference Proceeding Series},
volume = {382},
pages = {1137--1144},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1553374.1553519},
doi = {10.1145/1553374.1553519},
timestamp = {Tue, 06 Nov 2018 16:58:29 +0100},
biburl = {https://dblp.org/rec/conf/icml/XuWS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/WhiteB09,
author = {Martha White and
Michael H. Bowling},
editor = {Craig Boutilier},
title = {Learning a Value Analysis Tool for Agent Evaluation},
booktitle = {{IJCAI} 2009, Proceedings of the 21st International Joint Conference
on Artificial Intelligence, Pasadena, California, USA, July 11-17,
2009},
pages = {1976--1981},
year = {2009},
url = {http://ijcai.org/Proceedings/09/Papers/326.pdf},
timestamp = {Tue, 20 Aug 2019 16:16:40 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/WhiteB09.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 2024-04-25 01:29 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:
