Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Gheorghe Comanici
@article{DBLP:journals/corr/abs-2311-03583,
author = {Abbas Mehrabian and
Ankit Anand and
Hyunjik Kim and
Nicolas Sonnerat and
Matej Balog and
Gheorghe Comanici and
Tudor Berariu and
Andrew Lee and
Anian Ruoss and
Anna Bulanova and
Daniel Toyama and
Sam Blackwell and
Bernardino Romera{-}Paredes and
Petar Velickovic and
Laurent Orseau and
Joonkyung Lee and
Anurag Murty Naredla and
Doina Precup and
Adam Zsolt Wagner},
title = {Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu
Search},
journal = {CoRR},
volume = {abs/2311.03583},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.03583},
doi = {10.48550/ARXIV.2311.03583},
eprinttype = {arXiv},
eprint = {2311.03583},
timestamp = {Tue, 14 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-03583.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-09187,
author = {Kate Baumli and
Satinder Baveja and
Feryal M. P. Behbahani and
Harris Chan and
Gheorghe Comanici and
Sebastian Flennerhag and
Maxime Gazeau and
Kristian Holsheimer and
Dan Horgan and
Michael Laskin and
Clare Lyle and
Hussain Masoom and
Kay McKinney and
Volodymyr Mnih and
Alexander Neitz and
Fabio Pardo and
Jack Parker{-}Holder and
John Quan and
Tim Rockt{\"{a}}schel and
Himanshu Sahni and
Tom Schaul and
Yannick Schroecker and
Stephen Spencer and
Richie Steigerwald and
Luyu Wang and
Lei Zhang},
title = {Vision-Language Models as a Source of Rewards},
journal = {CoRR},
volume = {abs/2312.09187},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.09187},
doi = {10.48550/ARXIV.2312.09187},
eprinttype = {arXiv},
eprint = {2312.09187},
timestamp = {Tue, 09 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-09187.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-10374,
author = {Gheorghe Comanici and
Amelia Glaese and
Anita Gergely and
Daniel Toyama and
Zafarali Ahmed and
Tyler Jackson and
Philippe Hamel and
Doina Precup},
title = {Learning how to Interact with a Complex Interface using Hierarchical
Reinforcement Learning},
journal = {CoRR},
volume = {abs/2204.10374},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.10374},
doi = {10.48550/ARXIV.2204.10374},
eprinttype = {arXiv},
eprint = {2204.10374},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-10374.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KhetarpalACP21,
author = {Khimya Khetarpal and
Zafarali Ahmed and
Gheorghe Comanici and
Doina Precup},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Temporally Abstract Partial Models},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {1979--1991},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/0f3d014eead934bbdbacb62a01dc4831-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/KhetarpalACP21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-13231,
author = {Daniel Toyama and
Philippe Hamel and
Anita Gergely and
Gheorghe Comanici and
Amelia Glaese and
Zafarali Ahmed and
Tyler Jackson and
Shibl Mourad and
Doina Precup},
title = {AndroidEnv: {A} Reinforcement Learning Platform for Android},
journal = {CoRR},
volume = {abs/2105.13231},
year = {2021},
url = {https://arxiv.org/abs/2105.13231},
eprinttype = {arXiv},
eprint = {2105.13231},
timestamp = {Tue, 01 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-13231.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-13105,
author = {Andr{\'{e}} Barreto and
Diana Borsa and
Shaobo Hou and
Gheorghe Comanici and
Eser Ayg{\"{u}}n and
Philippe Hamel and
Daniel Toyama and
Jonathan J. Hunt and
Shibl Mourad and
David Silver and
Doina Precup},
title = {The Option Keyboard: Combining Skills in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2106.13105},
year = {2021},
url = {https://arxiv.org/abs/2106.13105},
eprinttype = {arXiv},
eprint = {2106.13105},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-13105.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-03213,
author = {Khimya Khetarpal and
Zafarali Ahmed and
Gheorghe Comanici and
Doina Precup},
title = {Temporally Abstract Partial Models},
journal = {CoRR},
volume = {abs/2108.03213},
year = {2021},
url = {https://arxiv.org/abs/2108.03213},
eprinttype = {arXiv},
eprint = {2108.03213},
timestamp = {Wed, 11 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-03213.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KhetarpalACAP20,
author = {Khimya Khetarpal and
Zafarali Ahmed and
Gheorghe Comanici and
David Abel and
Doina Precup},
title = {What can {I} do here? {A} Theory of Affordances in Reinforcement Learning},
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 = {5243--5253},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/khetarpal20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/KhetarpalACAP20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-15085,
author = {Khimya Khetarpal and
Zafarali Ahmed and
Gheorghe Comanici and
David Abel and
Doina Precup},
title = {What can {I} do here? {A} Theory of Affordances in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2006.15085},
year = {2020},
url = {https://arxiv.org/abs/2006.15085},
eprinttype = {arXiv},
eprint = {2006.15085},
timestamp = {Wed, 01 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-15085.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BarretoBHCAHTHM19,
author = {Andr{\'{e}} Barreto and
Diana Borsa and
Shaobo Hou and
Gheorghe Comanici and
Eser Ayg{\"{u}}n and
Philippe Hamel and
Daniel Toyama and
Jonathan J. Hunt and
Shibl Mourad and
David Silver and
Doina Precup},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {The Option Keyboard: Combining Skills in Reinforcement 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 = {13031--13041},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/251c5ffd6b62cc21c446c963c76cf214-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/BarretoBHCAHTHM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/RuanCPP15,
author = {Sherry Shanshan Ruan and
Gheorghe Comanici and
Prakash Panangaden and
Doina Precup},
editor = {Blai Bonet and
Sven Koenig},
title = {Representation Discovery for MDPs Using Bisimulation Metrics},
booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence,
January 25-30, 2015, Austin, Texas, {USA}},
pages = {3578--3584},
publisher = {{AAAI} Press},
year = {2015},
url = {https://doi.org/10.1609/aaai.v29i1.9701},
doi = {10.1609/AAAI.V29I1.9701},
timestamp = {Mon, 18 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/RuanCPP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/RuanCPP15a,
author = {Sherry Shanshan Ruan and
Gheorghe Comanici and
Prakash Panangaden and
Doina Precup},
editor = {Blai Bonet and
Sven Koenig},
title = {Representation Discovery for MDPs Using Bisimulation Metrics},
booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence,
January 25-30, 2015, Austin, Texas, {USA}},
pages = {4202--4203},
publisher = {{AAAI} Press},
year = {2015},
url = {https://doi.org/10.1609/aaai.v29i1.9747},
doi = {10.1609/AAAI.V29I1.9747},
timestamp = {Mon, 18 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/RuanCPP15a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ComaniciPP15,
author = {Gheorghe Comanici and
Doina Precup and
Prakash Panangaden},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Basis refinement strategies for linear value function approximation
in MDPs},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {2899--2907},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/a40511cad8383e5ae8ddd8b855d135da-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/ComaniciPP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/PaduraruPPC12,
author = {Cosmin Paduraru and
Doina Precup and
Joelle Pineau and
Gheorghe Comanici},
editor = {Marc Peter Deisenroth and
Csaba Szepesv{\'{a}}ri and
Jan Peters},
title = {An Empirical Analysis of Off-policy Learning in Discrete MDPs},
booktitle = {Proceedings of the Tenth European Workshop on Reinforcement Learning,
{EWRL} 2012, Edinburgh, Scotland, UK, June, 2012},
series = {{JMLR} Proceedings},
volume = {24},
pages = {89--102},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v24/paduraru12a.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/PaduraruPPC12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/qest/ComaniciPP12,
author = {Gheorghe Comanici and
Prakash Panangaden and
Doina Precup},
title = {On-the-Fly Algorithms for Bisimulation Metrics},
booktitle = {Ninth International Conference on Quantitative Evaluation of Systems,
{QEST} 2012, London, United Kingdom, September 17-20, 2012},
pages = {94--103},
publisher = {{IEEE} Computer Society},
year = {2012},
url = {https://doi.org/10.1109/QEST.2012.30},
doi = {10.1109/QEST.2012.30},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/qest/ComaniciPP12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ComaniciP11,
author = {Gheorghe Comanici and
Doina Precup},
editor = {Wolfram Burgard and
Dan Roth},
title = {Basis Function Discovery Using Spectral Clustering and Bisimulation
Metrics},
booktitle = {Proceedings of the Twenty-Fifth {AAAI} Conference on Artificial Intelligence,
{AAAI} 2011, San Francisco, California, USA, August 7-11, 2011},
pages = {325--330},
publisher = {{AAAI} Press},
year = {2011},
url = {https://doi.org/10.1609/aaai.v25i1.7918},
doi = {10.1609/AAAI.V25I1.7918},
timestamp = {Mon, 04 Sep 2023 16:05:54 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ComaniciP11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ComaniciP11a,
author = {Gheorghe Comanici and
Doina Precup},
editor = {Peter Vrancx and
Matthew Knudson and
Marek Grzes},
title = {Basis Function Discovery Using Spectral Clustering and Bisimulation
Metrics},
booktitle = {Adaptive and Learning Agents - International Workshop, {ALA} 2011,
Held at {AAMAS} 2011, Taipei, Taiwan, May 2, 2011, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {7113},
pages = {85--99},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-28499-1\_6},
doi = {10.1007/978-3-642-28499-1\_6},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/atal/ComaniciP11a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ComaniciP11,
author = {Gheorghe Comanici and
Doina Precup},
editor = {Liz Sonenberg and
Peter Stone and
Kagan Tumer and
Pinar Yolum},
title = {Basis function discovery using spectral clustering and bisimulation
metrics},
booktitle = {10th International Conference on Autonomous Agents and Multiagent
Systems {(AAMAS} 2011), Taipei, Taiwan, May 2-6, 2011, Volume 1-3},
pages = {1079--1080},
publisher = {{IFAAMAS}},
year = {2011},
url = {http://portal.acm.org/citation.cfm?id=2034427\&\#38;CFID=69154334\&\#38;CFTOKEN=45298625},
timestamp = {Fri, 18 Nov 2011 09:09:28 +0100},
biburl = {https://dblp.org/rec/conf/atal/ComaniciP11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ComaniciP10,
author = {Gheorghe Comanici and
Doina Precup},
editor = {Wiebe van der Hoek and
Gal A. Kaminka and
Yves Lesp{\'{e}}rance and
Michael Luck and
Sandip Sen},
title = {Optimal policy switching algorithms for reinforcement learning},
booktitle = {9th International Conference on Autonomous Agents and Multiagent Systems
{(AAMAS} 2010), Toronto, Canada, May 10-14, 2010, Volume 1-3},
pages = {709--714},
publisher = {{IFAAMAS}},
year = {2010},
url = {https://dl.acm.org/citation.cfm?id=1838300},
timestamp = {Fri, 30 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/ComaniciP10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-04-21 17:22 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:
