Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Marc Lanctot
@inproceedings{DBLP:conf/aaai/SychrovskySDBLS24,
author = {David Sychrovsky and
Michal Sustr and
Elnaz Davoodi and
Michael Bowling and
Marc Lanctot and
Martin Schmid},
editor = {Michael J. Wooldridge and
Jennifer G. Dy and
Sriraam Natarajan},
title = {Learning Not to Regret},
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 = {15202--15210},
publisher = {{AAAI} Press},
year = {2024},
url = {https://doi.org/10.1609/aaai.v38i14.29443},
doi = {10.1609/AAAI.V38I14.29443},
timestamp = {Tue, 02 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SychrovskySDBLS24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-05133,
author = {Siqi Liu and
Luke Marris and
Marc Lanctot and
Georgios Piliouras and
Joel Z. Leibo and
Nicolas Heess},
title = {Neural Population Learning beyond Symmetric Zero-sum Games},
journal = {CoRR},
volume = {abs/2401.05133},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.05133},
doi = {10.48550/ARXIV.2401.05133},
eprinttype = {arXiv},
eprint = {2401.05133},
timestamp = {Thu, 25 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-05133.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-01704,
author = {Ian Gemp and
Yoram Bachrach and
Marc Lanctot and
Roma Patel and
Vibhavari Dasagi and
Luke Marris and
Georgios Piliouras and
Siqi Liu and
Karl Tuyls},
title = {States as Strings as Strategies: Steering Language Models with Game-Theoretic
Solvers},
journal = {CoRR},
volume = {abs/2402.01704},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.01704},
doi = {10.48550/ARXIV.2402.01704},
eprinttype = {arXiv},
eprint = {2402.01704},
timestamp = {Fri, 09 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-01704.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-03928,
author = {Ian Gemp and
Marc Lanctot and
Luke Marris and
Yiran Mao and
Edgar A. Du{\'{e}}{\~{n}}ez{-}Guzm{\'{a}}n and
Sarah Perrin and
Andras Gyorgy and
Romuald Elie and
Georgios Piliouras and
Michael Kaisers and
Daniel Hennes and
Kalesha Bullard and
Kate Larson and
Yoram Bachrach},
title = {Approximating the Core via Iterative Coalition Sampling},
journal = {CoRR},
volume = {abs/2402.03928},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.03928},
doi = {10.48550/ARXIV.2402.03928},
eprinttype = {arXiv},
eprint = {2402.03928},
timestamp = {Mon, 12 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-03928.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-11835,
author = {Luca D'Amico{-}Wong and
Hugh Zhang and
Marc Lanctot and
David C. Parkes},
title = {Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret
Minimization},
journal = {CoRR},
volume = {abs/2402.11835},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.11835},
doi = {10.48550/ARXIV.2402.11835},
eprinttype = {arXiv},
eprint = {2402.11835},
timestamp = {Mon, 26 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-11835.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/LiLMMGHLBWM23,
author = {Zun Li and
Marc Lanctot and
Kevin R. McKee and
Luke Marris and
Ian Gemp and
Daniel Hennes and
Kate Larson and
Yoram Bachrach and
Michael P. Wellman and
Paul Muller},
editor = {Noa Agmon and
Bo An and
Alessandro Ricci and
William Yeoh},
title = {Search-Improved Game-Theoretic Multiagent Reinforcement Learning in
General and Negotiation Games},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2023, London, United Kingdom, 29 May
2023 - 2 June 2023},
pages = {2445--2447},
publisher = {{ACM}},
year = {2023},
url = {https://dl.acm.org/doi/10.5555/3545946.3598962},
doi = {10.5555/3545946.3598962},
timestamp = {Tue, 23 May 2023 14:27:14 +0200},
biburl = {https://dblp.org/rec/conf/atal/LiLMMGHLBWM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/McAleerFLS23,
author = {Stephen Marcus McAleer and
Gabriele Farina and
Marc Lanctot and
Tuomas Sandholm},
title = {{ESCHER:} Eschewing Importance Sampling in Games by Computing a History
Value Function to Estimate Regret},
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=35QyoZv8cKO},
timestamp = {Fri, 30 Jun 2023 14:38:38 +0200},
biburl = {https://dblp.org/rec/conf/iclr/McAleerFLS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/SokotaDKLLMBK23,
author = {Samuel Sokota and
Ryan D'Orazio and
J. Zico Kolter and
Nicolas Loizou and
Marc Lanctot and
Ioannis Mitliagkas and
Noam Brown and
Christian Kroer},
title = {A Unified Approach to Reinforcement Learning, Quantal Response Equilibria,
and Two-Player Zero-Sum Games},
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=DpE5UYUQzZH},
timestamp = {Fri, 30 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/SokotaDKLLMBK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-00797,
author = {Zun Li and
Marc Lanctot and
Kevin R. McKee and
Luke Marris and
Ian Gemp and
Daniel Hennes and
Paul Muller and
Kate Larson and
Yoram Bachrach and
Michael P. Wellman},
title = {Combining Tree-Search, Generative Models, and Nash Bargaining Concepts
in Game-Theoretic Reinforcement Learning},
journal = {CoRR},
volume = {abs/2302.00797},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.00797},
doi = {10.48550/ARXIV.2302.00797},
eprinttype = {arXiv},
eprint = {2302.00797},
timestamp = {Thu, 09 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-00797.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-01074,
author = {David Sychrovsky and
Michal Sustr and
Elnaz Davoodi and
Marc Lanctot and
Martin Schmid},
title = {Learning not to Regret},
journal = {CoRR},
volume = {abs/2303.01074},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.01074},
doi = {10.48550/ARXIV.2303.01074},
eprinttype = {arXiv},
eprint = {2303.01074},
timestamp = {Mon, 06 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-01074.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-03196,
author = {Marc Lanctot and
John Schultz and
Neil Burch and
Max Olan Smith and
Daniel Hennes and
Thomas W. Anthony and
Julien P{\'{e}}rolat},
title = {Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark
for Multiagent Reinforcement Learning},
journal = {CoRR},
volume = {abs/2303.03196},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.03196},
doi = {10.48550/ARXIV.2303.03196},
eprinttype = {arXiv},
eprint = {2303.03196},
timestamp = {Wed, 15 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-03196.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-03121,
author = {Marc Lanctot and
Kate Larson and
Yoram Bachrach and
Luke Marris and
Zun Li and
Avishkar Bhoopchand and
Thomas W. Anthony and
Brian Tanner and
Anna Koop},
title = {Evaluating Agents using Social Choice Theory},
journal = {CoRR},
volume = {abs/2312.03121},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.03121},
doi = {10.48550/ARXIV.2312.03121},
eprinttype = {arXiv},
eprint = {2312.03121},
timestamp = {Mon, 01 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-03121.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aicom/GempABBBCDVDEEH22,
author = {Ian Gemp and
Thomas W. Anthony and
Yoram Bachrach and
Avishkar Bhoopchand and
Kalesha Bullard and
Jerome T. Connor and
Vibhavari Dasagi and
Bart De Vylder and
Edgar A. Du{\'{e}}{\~{n}}ez{-}Guzm{\'{a}}n and
Romuald Elie and
Richard Everett and
Daniel Hennes and
Edward Hughes and
Mina Khan and
Marc Lanctot and
Kate Larson and
Guy Lever and
Siqi Liu and
Luke Marris and
Kevin R. McKee and
Paul Muller and
Julien P{\'{e}}rolat and
Florian Strub and
Andrea Tacchetti and
Eugene Tarassov and
Zhe Wang and
Karl Tuyls},
title = {Developing, evaluating and scaling learning agents in multi-agent
environments},
journal = {{AI} Commun.},
volume = {35},
number = {4},
pages = {271--284},
year = {2022},
url = {https://doi.org/10.3233/AIC-220113},
doi = {10.3233/AIC-220113},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aicom/GempABBBCDVDEEH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/GempSLBA0TEK22,
author = {Ian Gemp and
Rahul Savani and
Marc Lanctot and
Yoram Bachrach and
Thomas W. Anthony and
Richard Everett and
Andrea Tacchetti and
Tom Eccles and
J{\'{a}}nos Kram{\'{a}}r},
editor = {Piotr Faliszewski and
Viviana Mascardi and
Catherine Pelachaud and
Matthew E. Taylor},
title = {Sample-based Approximation of Nash in Large Many-Player Games via
Gradient Descent},
booktitle = {21st International Conference on Autonomous Agents and Multiagent
Systems, {AAMAS} 2022, Auckland, New Zealand, May 9-13, 2022},
pages = {507--515},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems
{(IFAAMAS)}},
year = {2022},
url = {https://www.ifaamas.org/Proceedings/aamas2022/pdfs/p507.pdf},
doi = {10.5555/3535850.3535908},
timestamp = {Wed, 06 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/GempSLBA0TEK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LiuLMH22,
author = {Siqi Liu and
Marc Lanctot and
Luke Marris and
Nicolas Heess},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in
Symmetric Zero-sum Games},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {13793--13806},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/liu22h.html},
timestamp = {Thu, 11 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/LiuLMH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/TimbersBLLSBSHB22,
author = {Finbarr Timbers and
Nolan Bard and
Edward Lockhart and
Marc Lanctot and
Martin Schmid and
Neil Burch and
Julian Schrittwieser and
Thomas Hubert and
Michael Bowling},
editor = {Luc De Raedt},
title = {Approximate Exploitability: Learning a Best Response},
booktitle = {Proceedings of the Thirty-First International Joint Conference on
Artificial Intelligence, {IJCAI} 2022, Vienna, Austria, 23-29 July
2022},
pages = {3487--3493},
publisher = {ijcai.org},
year = {2022},
url = {https://doi.org/10.24963/ijcai.2022/484},
doi = {10.24963/IJCAI.2022/484},
timestamp = {Wed, 27 Jul 2022 16:43:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/TimbersBLLSBSHB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-07700,
author = {Stephen McAleer and
Kevin Wang and
John B. Lanier and
Marc Lanctot and
Pierre Baldi and
Tuomas Sandholm and
Roy Fox},
title = {Anytime {PSRO} for Two-Player Zero-Sum Games},
journal = {CoRR},
volume = {abs/2201.07700},
year = {2022},
url = {https://arxiv.org/abs/2201.07700},
eprinttype = {arXiv},
eprint = {2201.07700},
timestamp = {Thu, 28 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-07700.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-15879,
author = {Siqi Liu and
Marc Lanctot and
Luke Marris and
Nicolas Heess},
title = {Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in
Symmetric Zero-sum Games},
journal = {CoRR},
volume = {abs/2205.15879},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.15879},
doi = {10.48550/ARXIV.2205.15879},
eprinttype = {arXiv},
eprint = {2205.15879},
timestamp = {Thu, 11 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-15879.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-04122,
author = {Stephen McAleer and
Gabriele Farina and
Marc Lanctot and
Tuomas Sandholm},
title = {{ESCHER:} Eschewing Importance Sampling in Games by Computing a History
Value Function to Estimate Regret},
journal = {CoRR},
volume = {abs/2206.04122},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.04122},
doi = {10.48550/ARXIV.2206.04122},
eprinttype = {arXiv},
eprint = {2206.04122},
timestamp = {Tue, 14 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-04122.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-05825,
author = {Samuel Sokota and
Ryan D'Orazio and
J. Zico Kolter and
Nicolas Loizou and
Marc Lanctot and
Ioannis Mitliagkas and
Noam Brown and
Christian Kroer},
title = {A Unified Approach to Reinforcement Learning, Quantal Response Equilibria,
and Two-Player Zero-Sum Games},
journal = {CoRR},
volume = {abs/2206.05825},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.05825},
doi = {10.48550/ARXIV.2206.05825},
eprinttype = {arXiv},
eprint = {2206.05825},
timestamp = {Mon, 20 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-05825.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-15378,
author = {Julien P{\'{e}}rolat and
Bart De Vylder and
Daniel Hennes and
Eugene Tarassov and
Florian Strub and
Vincent de Boer and
Paul Muller and
Jerome T. Connor and
Neil Burch and
Thomas W. Anthony and
Stephen McAleer and
Romuald Elie and
Sarah H. Cen and
Zhe Wang and
Audrunas Gruslys and
Aleksandra Malysheva and
Mina Khan and
Sherjil Ozair and
Finbarr Timbers and
Toby Pohlen and
Tom Eccles and
Mark Rowland and
Marc Lanctot and
Jean{-}Baptiste Lespiau and
Bilal Piot and
Shayegan Omidshafiei and
Edward Lockhart and
Laurent Sifre and
Nathalie Beauguerlange and
R{\'{e}}mi Munos and
David Silver and
Satinder Singh and
Demis Hassabis and
Karl Tuyls},
title = {Mastering the Game of Stratego with Model-Free Multiagent Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2206.15378},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.15378},
doi = {10.48550/ARXIV.2206.15378},
eprinttype = {arXiv},
eprint = {2206.15378},
timestamp = {Wed, 28 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-15378.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-10958,
author = {Ian Gemp and
Thomas W. Anthony and
Yoram Bachrach and
Avishkar Bhoopchand and
Kalesha Bullard and
Jerome T. Connor and
Vibhavari Dasagi and
Bart De Vylder and
Edgar A. Du{\'{e}}{\~{n}}ez{-}Guzm{\'{a}}n and
Romuald Elie and
Richard Everett and
Daniel Hennes and
Edward Hughes and
Mina Khan and
Marc Lanctot and
Kate Larson and
Guy Lever and
Siqi Liu and
Luke Marris and
Kevin R. McKee and
Paul Muller and
Julien P{\'{e}}rolat and
Florian Strub and
Andrea Tacchetti and
Eugene Tarassov and
Zhe Wang and
Karl Tuyls},
title = {Developing, Evaluating and Scaling Learning Agents in Multi-Agent
Environments},
journal = {CoRR},
volume = {abs/2209.10958},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.10958},
doi = {10.48550/ARXIV.2209.10958},
eprinttype = {arXiv},
eprint = {2209.10958},
timestamp = {Fri, 06 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-10958.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-02205,
author = {Luke Marris and
Marc Lanctot and
Ian Gemp and
Shayegan Omidshafiei and
Stephen McAleer and
Jerome T. Connor and
Karl Tuyls and
Thore Graepel},
title = {Game Theoretic Rating in N-player general-sum games with Equilibria},
journal = {CoRR},
volume = {abs/2210.02205},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.02205},
doi = {10.48550/ARXIV.2210.02205},
eprinttype = {arXiv},
eprint = {2210.02205},
timestamp = {Fri, 07 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-02205.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/MorrillDSLWGB21,
author = {Dustin Morrill and
Ryan D'Orazio and
Reca Sarfati and
Marc Lanctot and
James R. Wright and
Amy R. Greenwald and
Michael Bowling},
title = {Hindsight and Sequential Rationality of Correlated Play},
booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI}
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9,
2021},
pages = {5584--5594},
publisher = {{AAAI} Press},
year = {2021},
url = {https://doi.org/10.1609/aaai.v35i6.16702},
doi = {10.1609/AAAI.V35I6.16702},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/MorrillDSLWGB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SokotaLTDDBSBL21,
author = {Samuel Sokota and
Edward Lockhart and
Finbarr Timbers and
Elnaz Davoodi and
Ryan D'Orazio and
Neil Burch and
Martin Schmid and
Michael Bowling and
Marc Lanctot},
title = {Solving Common-Payoff Games with Approximate Policy Iteration},
booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI}
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9,
2021},
pages = {9695--9703},
publisher = {{AAAI} Press},
year = {2021},
url = {https://doi.org/10.1609/aaai.v35i11.17166},
doi = {10.1609/AAAI.V35I11.17166},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SokotaLTDDBSBL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SustrSMBLB21,
author = {Michal Sustr and
Martin Schmid and
Matej Moravc{\'{\i}}k and
Neil Burch and
Marc Lanctot and
Michael Bowling},
editor = {Frank Dignum and
Alessio Lomuscio and
Ulle Endriss and
Ann Now{\'{e}}},
title = {Sound Algorithms in Imperfect Information Games},
booktitle = {{AAMAS} '21: 20th International Conference on Autonomous Agents and
Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021},
pages = {1674--1676},
publisher = {{ACM}},
year = {2021},
url = {https://www.ifaamas.org/Proceedings/aamas2021/pdfs/p1674.pdf},
doi = {10.5555/3463952.3464197},
timestamp = {Wed, 20 Jul 2022 17:03:47 +0200},
biburl = {https://dblp.org/rec/conf/atal/SustrSMBLB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MarrisMLTG21,
author = {Luke Marris and
Paul Muller and
Marc Lanctot and
Karl Tuyls and
Thore Graepel},
editor = {Marina Meila and
Tong Zhang},
title = {Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {7480--7491},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/marris21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MarrisMLTG21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MorrillDLWBG21,
author = {Dustin Morrill and
Ryan D'Orazio and
Marc Lanctot and
James R. Wright and
Michael Bowling and
Amy R. Greenwald},
editor = {Marina Meila and
Tong Zhang},
title = {Efficient Deviation Types and Learning for Hindsight Rationality in
Extensive-Form Games},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {7818--7828},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/morrill21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MorrillDLWBG21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/PerolatMLOROBAB21,
author = {Julien P{\'{e}}rolat and
R{\'{e}}mi Munos and
Jean{-}Baptiste Lespiau and
Shayegan Omidshafiei and
Mark Rowland and
Pedro A. Ortega and
Neil Burch and
Thomas W. Anthony and
David Balduzzi and
Bart De Vylder and
Georgios Piliouras and
Marc Lanctot and
Karl Tuyls},
editor = {Marina Meila and
Tong Zhang},
title = {From Poincar{\'{e}} Recurrence to Convergence in Imperfect Information
Games: Finding Equilibrium via Regularization},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {8525--8535},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/perolat21a.html},
timestamp = {Wed, 28 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/PerolatMLOROBAB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GuptaLL21,
author = {Abhinav Gupta and
Marc Lanctot and
Angeliki Lazaridou},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Dynamic population-based meta-learning for multi-agent communication
with natural language},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {16899--16912},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/8caa38721906c1a0bb95c80fab33a893-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/GuptaLL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-04237,
author = {Samuel Sokota and
Edward Lockhart and
Finbarr Timbers and
Elnaz Davoodi and
Ryan D'Orazio and
Neil Burch and
Martin Schmid and
Michael Bowling and
Marc Lanctot},
title = {Solving Common-Payoff Games with Approximate Policy Iteration},
journal = {CoRR},
volume = {abs/2101.04237},
year = {2021},
url = {https://arxiv.org/abs/2101.04237},
eprinttype = {arXiv},
eprint = {2101.04237},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-04237.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-06973,
author = {Dustin Morrill and
Ryan D'Orazio and
Marc Lanctot and
James R. Wright and
Michael Bowling and
Amy Greenwald},
title = {Efficient Deviation Types and Learning for Hindsight Rationality in
Extensive-Form Games},
journal = {CoRR},
volume = {abs/2102.06973},
year = {2021},
url = {https://arxiv.org/abs/2102.06973},
eprinttype = {arXiv},
eprint = {2102.06973},
timestamp = {Thu, 18 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-06973.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-01285,
author = {Ian Gemp and
Rahul Savani and
Marc Lanctot and
Yoram Bachrach and
Thomas W. Anthony and
Richard Everett and
Andrea Tacchetti and
Tom Eccles and
J{\'{a}}nos Kram{\'{a}}r},
title = {Sample-based Approximation of Nash in Large Many-Player Games via
Gradient Descent},
journal = {CoRR},
volume = {abs/2106.01285},
year = {2021},
url = {https://arxiv.org/abs/2106.01285},
eprinttype = {arXiv},
eprint = {2106.01285},
timestamp = {Wed, 06 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-01285.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-09435,
author = {Luke Marris and
Paul Muller and
Marc Lanctot and
Karl Tuyls and
Thore Graepel},
title = {Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers},
journal = {CoRR},
volume = {abs/2106.09435},
year = {2021},
url = {https://arxiv.org/abs/2106.09435},
eprinttype = {arXiv},
eprint = {2106.09435},
timestamp = {Tue, 29 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-09435.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-14241,
author = {Abhinav Gupta and
Marc Lanctot and
Angeliki Lazaridou},
title = {Dynamic population-based meta-learning for multi-agent communication
with natural language},
journal = {CoRR},
volume = {abs/2110.14241},
year = {2021},
url = {https://arxiv.org/abs/2110.14241},
eprinttype = {arXiv},
eprint = {2110.14241},
timestamp = {Wed, 03 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-14241.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-03178,
author = {Martin Schmid and
Matej Moravcik and
Neil Burch and
Rudolf Kadlec and
Joshua Davidson and
Kevin Waugh and
Nolan Bard and
Finbarr Timbers and
Marc Lanctot and
G. Zacharias Holland and
Elnaz Davoodi and
Alden Christianson and
Michael Bowling},
title = {Player of Games},
journal = {CoRR},
volume = {abs/2112.03178},
year = {2021},
url = {https://arxiv.org/abs/2112.03178},
eprinttype = {arXiv},
eprint = {2112.03178},
timestamp = {Sat, 07 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-03178.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/TuylsPLHELSG20,
author = {Karl Tuyls and
Julien P{\'{e}}rolat and
Marc Lanctot and
Edward Hughes and
Richard Everett and
Joel Z. Leibo and
Csaba Szepesv{\'{a}}ri and
Thore Graepel},
title = {Bounds and dynamics for empirical game theoretic analysis},
journal = {Auton. Agents Multi Agent Syst.},
volume = {34},
number = {1},
pages = {7},
year = {2020},
url = {https://doi.org/10.1007/s10458-019-09432-y},
doi = {10.1007/S10458-019-09432-Y},
timestamp = {Fri, 09 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aamas/TuylsPLHELSG20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ai/BardFCBLSPDMHDM20,
author = {Nolan Bard and
Jakob N. Foerster and
Sarath Chandar and
Neil Burch and
Marc Lanctot and
H. Francis Song and
Emilio Parisotto and
Vincent Dumoulin and
Subhodeep Moitra and
Edward Hughes and
Iain Dunning and
Shibl Mourad and
Hugo Larochelle and
Marc G. Bellemare and
Michael Bowling},
title = {The Hanabi challenge: {A} new frontier for {AI} research},
journal = {Artif. Intell.},
volume = {280},
pages = {103216},
year = {2020},
url = {https://doi.org/10.1016/j.artint.2019.103216},
doi = {10.1016/J.ARTINT.2019.103216},
timestamp = {Fri, 14 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ai/BardFCBLSPDMHDM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ai/BachrachEHLLLJC20,
author = {Yoram Bachrach and
Richard Everett and
Edward Hughes and
Angeliki Lazaridou and
Joel Z. Leibo and
Marc Lanctot and
Michael Johanson and
Wojciech M. Czarnecki and
Thore Graepel},
title = {Negotiating team formation using deep reinforcement learning},
journal = {Artif. Intell.},
volume = {288},
pages = {103356},
year = {2020},
url = {https://doi.org/10.1016/j.artint.2020.103356},
doi = {10.1016/J.ARTINT.2020.103356},
timestamp = {Thu, 16 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ai/BachrachEHLLLJC20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/HennesMOMPLGLPD20,
author = {Daniel Hennes and
Dustin Morrill and
Shayegan Omidshafiei and
R{\'{e}}mi Munos and
Julien P{\'{e}}rolat and
Marc Lanctot and
Audrunas Gruslys and
Jean{-}Baptiste Lespiau and
Paavo Parmas and
Edgar A. Du{\'{e}}{\~{n}}ez{-}Guzm{\'{a}}n and
Karl Tuyls},
editor = {Amal El Fallah Seghrouchni and
Gita Sukthankar and
Bo An and
Neil Yorke{-}Smith},
title = {Neural Replicator Dynamics: Multiagent Learning via Hedging Policy
Gradients},
booktitle = {Proceedings of the 19th International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} '20, Auckland, New Zealand, May 9-13,
2020},
pages = {492--501},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
year = {2020},
url = {https://dl.acm.org/doi/10.5555/3398761.3398822},
doi = {10.5555/3398761.3398822},
timestamp = {Tue, 26 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/HennesMOMPLGLPD20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/MullerORTPLHMLH20,
author = {Paul Muller and
Shayegan Omidshafiei and
Mark Rowland and
Karl Tuyls and
Julien P{\'{e}}rolat and
Siqi Liu and
Daniel Hennes and
Luke Marris and
Marc Lanctot and
Edward Hughes and
Zhe Wang and
Guy Lever and
Nicolas Heess and
Thore Graepel and
R{\'{e}}mi Munos},
title = {A Generalized Training Approach for Multiagent 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=Bkl5kxrKDr},
timestamp = {Thu, 11 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/MullerORTPLHMLH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MunosPLRVLTHOGA20,
author = {R{\'{e}}mi Munos and
Julien P{\'{e}}rolat and
Jean{-}Baptiste Lespiau and
Mark Rowland and
Bart De Vylder and
Marc Lanctot and
Finbarr Timbers and
Daniel Hennes and
Shayegan Omidshafiei and
Audrunas Gruslys and
Mohammad Gheshlaghi Azar and
Edward Lockhart and
Karl Tuyls},
title = {Fast computation of Nash Equilibria in Imperfect Information Games},
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 = {7119--7129},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/munos20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/MunosPLRVLTHOGA20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AnthonyETKGHPLP20,
author = {Thomas W. Anthony and
Tom Eccles and
Andrea Tacchetti and
J{\'{a}}nos Kram{\'{a}}r and
Ian Gemp and
Thomas C. Hudson and
Nicolas Porcel and
Marc Lanctot and
Julien P{\'{e}}rolat and
Richard Everett and
Satinder Singh and
Thore Graepel and
Yoram Bachrach},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Learning to Play No-Press Diplomacy with Best Response Policy Iteration},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/d1419302db9c022ab1d48681b13d5f8b-Abstract.html},
timestamp = {Wed, 06 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/AnthonyETKGHPLP20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-08456,
author = {Julien P{\'{e}}rolat and
R{\'{e}}mi Munos and
Jean{-}Baptiste Lespiau and
Shayegan Omidshafiei and
Mark Rowland and
Pedro A. Ortega and
Neil Burch and
Thomas W. Anthony and
David Balduzzi and
Bart De Vylder and
Georgios Piliouras and
Marc Lanctot and
Karl Tuyls},
title = {From Poincar{\'{e}} Recurrence to Convergence in Imperfect Information
Games: Finding Equilibrium via Regularization},
journal = {CoRR},
volume = {abs/2002.08456},
year = {2020},
url = {https://arxiv.org/abs/2002.08456},
eprinttype = {arXiv},
eprint = {2002.08456},
timestamp = {Wed, 28 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-08456.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2004-09677,
author = {Finbarr Timbers and
Edward Lockhart and
Martin Schmid and
Marc Lanctot and
Michael Bowling},
title = {Approximate exploitability: Learning a best response in large games},
journal = {CoRR},
volume = {abs/2004.09677},
year = {2020},
url = {https://arxiv.org/abs/2004.09677},
eprinttype = {arXiv},
eprint = {2004.09677},
timestamp = {Tue, 28 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2004-09677.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-04635,
author = {Thomas W. Anthony and
Tom Eccles and
Andrea Tacchetti and
J{\'{a}}nos Kram{\'{a}}r and
Ian Gemp and
Thomas C. Hudson and
Nicolas Porcel and
Marc Lanctot and
Julien P{\'{e}}rolat and
Richard Everett and
Satinder Singh and
Thore Graepel and
Yoram Bachrach},
title = {Learning to Play No-Press Diplomacy with Best Response Policy Iteration},
journal = {CoRR},
volume = {abs/2006.04635},
year = {2020},
url = {https://arxiv.org/abs/2006.04635},
eprinttype = {arXiv},
eprint = {2006.04635},
timestamp = {Wed, 06 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-04635.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-08740,
author = {Michal Sustr and
Martin Schmid and
Matej Moravc{\'{\i}}k and
Neil Burch and
Marc Lanctot and
Michael Bowling},
title = {Sound Search in Imperfect Information Games},
journal = {CoRR},
volume = {abs/2006.08740},
year = {2020},
url = {https://arxiv.org/abs/2006.08740},
eprinttype = {arXiv},
eprint = {2006.08740},
timestamp = {Wed, 17 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-08740.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2008-12234,
author = {Audrunas Gruslys and
Marc Lanctot and
R{\'{e}}mi Munos and
Finbarr Timbers and
Martin Schmid and
Julien P{\'{e}}rolat and
Dustin Morrill and
Vin{\'{\i}}cius Flores Zambaldi and
Jean{-}Baptiste Lespiau and
John Schultz and
Mohammad Gheshlaghi Azar and
Michael Bowling and
Karl Tuyls},
title = {The Advantage Regret-Matching Actor-Critic},
journal = {CoRR},
volume = {abs/2008.12234},
year = {2020},
url = {https://arxiv.org/abs/2008.12234},
eprinttype = {arXiv},
eprint = {2008.12234},
timestamp = {Tue, 15 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2008-12234.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-10380,
author = {Yoram Bachrach and
Richard Everett and
Edward Hughes and
Angeliki Lazaridou and
Joel Z. Leibo and
Marc Lanctot and
Michael Johanson and
Wojciech M. Czarnecki and
Thore Graepel},
title = {Negotiating Team Formation Using Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/2010.10380},
year = {2020},
url = {https://arxiv.org/abs/2010.10380},
eprinttype = {arXiv},
eprint = {2010.10380},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-10380.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-05874,
author = {Dustin Morrill and
Ryan D'Orazio and
Reca Sarfati and
Marc Lanctot and
James R. Wright and
Amy Greenwald and
Michael Bowling},
title = {Hindsight and Sequential Rationality of Correlated Play},
journal = {CoRR},
volume = {abs/2012.05874},
year = {2020},
url = {https://arxiv.org/abs/2012.05874},
eprinttype = {arXiv},
eprint = {2012.05874},
timestamp = {Sat, 02 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-05874.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aim/BarashCCCEFGGhH19,
author = {Guy Barash and
Mauricio Castillo{-}Effen and
Niyati Chhaya and
Peter Clark and
Hu{\'{a}}scar Espinoza and
Eitan Farchi and
Christopher W. Geib and
Odd Erik Gundersen and
Se{\'{a}}n {\'{O}} h{\'{E}}igeartaigh and
Jos{\'{e}} Hern{\'{a}}ndez{-}Orallo and
Chiori Hori and
Xiaowei Huang and
Kokil Jaidka and
Pavan Kapanipathi and
Sarah Keren and
Seokhwan Kim and
Marc Lanctot and
Danny Lange and
Julian J. McAuley and
David R. Martinez and
Marwan Mattar and
Mausam and
Martin Michalowski and
Reuth Mirsky and
Roozbeh Mottaghi and
Joseph C. Osborn and
Julien P{\'{e}}rolat and
Martin Schmid and
Arash Shaban{-}Nejad and
Onn Shehory and
Biplav Srivastava and
William W. Streilein and
Kartik Talamadupula and
Julian Togelius and
Koichiro Yoshino and
Quanshi Zhang and
Imed Zitouni},
title = {Reports of the Workshops Held at the 2019 {AAAI} Conference on Artificial
Intelligence},
journal = {{AI} Mag.},
volume = {40},
number = {3},
pages = {67--78},
year = {2019},
url = {https://doi.org/10.1609/aimag.v40i3.4981},
doi = {10.1609/AIMAG.V40I3.4981},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/aim/BarashCCCEFGGhH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SchmidBLMKB19,
author = {Martin Schmid and
Neil Burch and
Marc Lanctot and
Matej Moravcik and
Rudolf Kadlec and
Michael Bowling},
title = {Variance Reduction in Monte Carlo Counterfactual Regret Minimization
{(VR-MCCFR)} for Extensive Form Games Using Baselines},
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 = {2157--2164},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33012157},
doi = {10.1609/AAAI.V33I01.33012157},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SchmidBLMKB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/LockhartLPLMTT19,
author = {Edward Lockhart and
Marc Lanctot and
Julien P{\'{e}}rolat and
Jean{-}Baptiste Lespiau and
Dustin Morrill and
Finbarr Timbers and
Karl Tuyls},
editor = {Sarit Kraus},
title = {Computing Approximate Equilibria in Sequential Adversarial Games by
Exploitability Descent},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16,
2019},
pages = {464--470},
publisher = {ijcai.org},
year = {2019},
url = {https://doi.org/10.24963/ijcai.2019/66},
doi = {10.24963/IJCAI.2019/66},
timestamp = {Tue, 20 Aug 2019 16:18:18 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/LockhartLPLMTT19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-00506,
author = {Nolan Bard and
Jakob N. Foerster and
Sarath Chandar and
Neil Burch and
Marc Lanctot and
H. Francis Song and
Emilio Parisotto and
Vincent Dumoulin and
Subhodeep Moitra and
Edward Hughes and
Iain Dunning and
Shibl Mourad and
Hugo Larochelle and
Marc G. Bellemare and
Michael Bowling},
title = {The Hanabi Challenge: {A} New Frontier for {AI} Research},
journal = {CoRR},
volume = {abs/1902.00506},
year = {2019},
url = {http://arxiv.org/abs/1902.00506},
eprinttype = {arXiv},
eprint = {1902.00506},
timestamp = {Fri, 09 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-00506.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-00742,
author = {Joel Z. Leibo and
Edward Hughes and
Marc Lanctot and
Thore Graepel},
title = {Autocurricula and the Emergence of Innovation from Social Interaction:
{A} Manifesto for Multi-Agent Intelligence Research},
journal = {CoRR},
volume = {abs/1903.00742},
year = {2019},
url = {http://arxiv.org/abs/1903.00742},
eprinttype = {arXiv},
eprint = {1903.00742},
timestamp = {Fri, 09 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1903-00742.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-01373,
author = {Shayegan Omidshafiei and
Christos H. Papadimitriou and
Georgios Piliouras and
Karl Tuyls and
Mark Rowland and
Jean{-}Baptiste Lespiau and
Wojciech M. Czarnecki and
Marc Lanctot and
Julien P{\'{e}}rolat and
R{\'{e}}mi Munos},
title = {{\(\alpha\)}-Rank: Multi-Agent Evaluation by Evolution},
journal = {CoRR},
volume = {abs/1903.01373},
year = {2019},
url = {http://arxiv.org/abs/1903.01373},
eprinttype = {arXiv},
eprint = {1903.01373},
timestamp = {Tue, 28 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1903-01373.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-05614,
author = {Edward Lockhart and
Marc Lanctot and
Julien P{\'{e}}rolat and
Jean{-}Baptiste Lespiau and
Dustin Morrill and
Finbarr Timbers and
Karl Tuyls},
title = {Computing Approximate Equilibria in Sequential Adversarial Games by
Exploitability Descent},
journal = {CoRR},
volume = {abs/1903.05614},
year = {2019},
url = {http://arxiv.org/abs/1903.05614},
eprinttype = {arXiv},
eprint = {1903.05614},
timestamp = {Sun, 31 Mar 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1903-05614.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-00190,
author = {Shayegan Omidshafiei and
Daniel Hennes and
Dustin Morrill and
R{\'{e}}mi Munos and
Julien P{\'{e}}rolat and
Marc Lanctot and
Audrunas Gruslys and
Jean{-}Baptiste Lespiau and
Karl Tuyls},
title = {Neural Replicator Dynamics},
journal = {CoRR},
volume = {abs/1906.00190},
year = {2019},
url = {http://arxiv.org/abs/1906.00190},
eprinttype = {arXiv},
eprint = {1906.00190},
timestamp = {Thu, 13 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-00190.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-09453,
author = {Marc Lanctot and
Edward Lockhart and
Jean{-}Baptiste Lespiau and
Vin{\'{\i}}cius Flores Zambaldi and
Satyaki Upadhyay and
Julien P{\'{e}}rolat and
Sriram Srinivasan and
Finbarr Timbers and
Karl Tuyls and
Shayegan Omidshafiei and
Daniel Hennes and
Dustin Morrill and
Paul Muller and
Timo Ewalds and
Ryan Faulkner and
J{\'{a}}nos Kram{\'{a}}r and
Bart De Vylder and
Brennan Saeta and
James Bradbury and
David Ding and
Sebastian Borgeaud and
Matthew Lai and
Julian Schrittwieser and
Thomas W. Anthony and
Edward Hughes and
Ivo Danihelka and
Jonah Ryan{-}Davis},
title = {OpenSpiel: {A} Framework for Reinforcement Learning in Games},
journal = {CoRR},
volume = {abs/1908.09453},
year = {2019},
url = {http://arxiv.org/abs/1908.09453},
eprinttype = {arXiv},
eprint = {1908.09453},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-09453.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-12823,
author = {Paul Muller and
Shayegan Omidshafiei and
Mark Rowland and
Karl Tuyls and
Julien P{\'{e}}rolat and
Siqi Liu and
Daniel Hennes and
Luke Marris and
Marc Lanctot and
Edward Hughes and
Zhe Wang and
Guy Lever and
Nicolas Heess and
Thore Graepel and
R{\'{e}}mi Munos},
title = {A Generalized Training Approach for Multiagent Learning},
journal = {CoRR},
volume = {abs/1909.12823},
year = {2019},
url = {http://arxiv.org/abs/1909.12823},
eprinttype = {arXiv},
eprint = {1909.12823},
timestamp = {Thu, 11 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-12823.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/HesterVPLSPHQSO18,
author = {Todd Hester and
Matej Vecer{\'{\i}}k and
Olivier Pietquin and
Marc Lanctot and
Tom Schaul and
Bilal Piot and
Dan Horgan and
John Quan and
Andrew Sendonaris and
Ian Osband and
Gabriel Dulac{-}Arnold and
John P. Agapiou and
Joel Z. Leibo and
Audrunas Gruslys},
editor = {Sheila A. McIlraith and
Kilian Q. Weinberger},
title = {Deep Q-learning From Demonstrations},
booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence,
(AAAI-18), the 30th innovative Applications of Artificial Intelligence
(IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in
Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February
2-7, 2018},
pages = {3223--3230},
publisher = {{AAAI} Press},
year = {2018},
url = {https://doi.org/10.1609/aaai.v32i1.11757},
doi = {10.1609/AAAI.V32I1.11757},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/HesterVPLSPHQSO18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/TuylsPLLG18,
author = {Karl Tuyls and
Julien P{\'{e}}rolat and
Marc Lanctot and
Joel Z. Leibo and
Thore Graepel},
editor = {Elisabeth Andr{\'{e}} and
Sven Koenig and
Mehdi Dastani and
Gita Sukthankar},
title = {A Generalised Method for Empirical Game Theoretic Analysis},
booktitle = {Proceedings of the 17th International Conference on Autonomous Agents
and MultiAgent Systems, {AAMAS} 2018, Stockholm, Sweden, July 10-15,
2018},
pages = {77--85},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems
Richland, SC, {USA} / {ACM}},
year = {2018},
url = {http://dl.acm.org/citation.cfm?id=3237402},
timestamp = {Sat, 30 Sep 2023 09:34:53 +0200},
biburl = {https://dblp.org/rec/conf/atal/TuylsPLLG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/SunehagLGCZJLSL18,
author = {Peter Sunehag and
Guy Lever and
Audrunas Gruslys and
Wojciech Marian Czarnecki and
Vin{\'{\i}}cius Flores Zambaldi and
Max Jaderberg and
Marc Lanctot and
Nicolas Sonnerat and
Joel Z. Leibo and
Karl Tuyls and
Thore Graepel},
editor = {Elisabeth Andr{\'{e}} and
Sven Koenig and
Mehdi Dastani and
Gita Sukthankar},
title = {Value-Decomposition Networks For Cooperative Multi-Agent Learning
Based On Team Reward},
booktitle = {Proceedings of the 17th International Conference on Autonomous Agents
and MultiAgent Systems, {AAMAS} 2018, Stockholm, Sweden, July 10-15,
2018},
pages = {2085--2087},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems
Richland, SC, {USA} / {ACM}},
year = {2018},
url = {http://dl.acm.org/citation.cfm?id=3238080},
timestamp = {Tue, 17 Jul 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/SunehagLGCZJLSL18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/CaoLLLTC18,
author = {Kris Cao and
Angeliki Lazaridou and
Marc Lanctot and
Joel Z. Leibo and
Karl Tuyls and
Stephen Clark},
title = {Emergent Communication through Negotiation},
booktitle = {6th International Conference on Learning Representations, {ICLR} 2018,
Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=Hk6WhagRW},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/CaoLLLTC18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SrinivasanLZPTM18,
author = {Sriram Srinivasan and
Marc Lanctot and
Vin{\'{\i}}cius Flores Zambaldi and
Julien P{\'{e}}rolat and
Karl Tuyls and
R{\'{e}}mi Munos and
Michael Bowling},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {Actor-Critic Policy Optimization in Partially Observable Multiagent
Environments},
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 = {3426--3439},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/e22dd5dabde45eda5a1a67772c8e25dd-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/SrinivasanLZPTM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-06376,
author = {Karl Tuyls and
Julien P{\'{e}}rolat and
Marc Lanctot and
Joel Z. Leibo and
Thore Graepel},
title = {A Generalised Method for Empirical Game Theoretic Analysis},
journal = {CoRR},
volume = {abs/1803.06376},
year = {2018},
url = {http://arxiv.org/abs/1803.06376},
eprinttype = {arXiv},
eprint = {1803.06376},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-06376.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-03980,
author = {Kris Cao and
Angeliki Lazaridou and
Marc Lanctot and
Joel Z. Leibo and
Karl Tuyls and
Stephen Clark},
title = {Emergent Communication through Negotiation},
journal = {CoRR},
volume = {abs/1804.03980},
year = {2018},
url = {http://arxiv.org/abs/1804.03980},
eprinttype = {arXiv},
eprint = {1804.03980},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-03980.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-03057,
author = {Martin Schmid and
Neil Burch and
Marc Lanctot and
Matej Moravcik and
Rudolf Kadlec and
Michael Bowling},
title = {Variance Reduction in Monte Carlo Counterfactual Regret Minimization
{(VR-MCCFR)} for Extensive Form Games using Baselines},
journal = {CoRR},
volume = {abs/1809.03057},
year = {2018},
url = {http://arxiv.org/abs/1809.03057},
eprinttype = {arXiv},
eprint = {1809.03057},
timestamp = {Fri, 05 Oct 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-03057.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-09026,
author = {Sriram Srinivasan and
Marc Lanctot and
Vin{\'{\i}}cius Flores Zambaldi and
Julien P{\'{e}}rolat and
Karl Tuyls and
R{\'{e}}mi Munos and
Michael Bowling},
title = {Actor-Critic Policy Optimization in Partially Observable Multiagent
Environments},
journal = {CoRR},
volume = {abs/1810.09026},
year = {2018},
url = {http://arxiv.org/abs/1810.09026},
eprinttype = {arXiv},
eprint = {1810.09026},
timestamp = {Fri, 04 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-09026.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/LeiboZLMG17,
author = {Joel Z. Leibo and
Vin{\'{\i}}cius Flores Zambaldi and
Marc Lanctot and
Janusz Marecki and
Thore Graepel},
editor = {Kate Larson and
Michael Winikoff and
Sanmay Das and
Edmund H. Durfee},
title = {Multi-agent Reinforcement Learning in Sequential Social Dilemmas},
booktitle = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent
Systems, {AAMAS} 2017, S{\~{a}}o Paulo, Brazil, May 8-12, 2017},
pages = {464--473},
publisher = {{ACM}},
year = {2017},
url = {http://dl.acm.org/citation.cfm?id=3091194},
timestamp = {Wed, 27 Sep 2017 07:24:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/LeiboZLMG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LanctotZGLTPSG17,
author = {Marc Lanctot and
Vin{\'{\i}}cius Flores Zambaldi and
Audrunas Gruslys and
Angeliki Lazaridou and
Karl Tuyls and
Julien P{\'{e}}rolat and
David Silver and
Thore Graepel},
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 = {A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {4190--4203},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/3323fe11e9595c09af38fe67567a9394-Abstract.html},
timestamp = {Thu, 21 Jan 2021 13:58:27 +0100},
biburl = {https://dblp.org/rec/conf/nips/LanctotZGLTPSG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LeiboZLMG17,
author = {Joel Z. Leibo and
Vin{\'{\i}}cius Flores Zambaldi and
Marc Lanctot and
Janusz Marecki and
Thore Graepel},
title = {Multi-agent Reinforcement Learning in Sequential Social Dilemmas},
journal = {CoRR},
volume = {abs/1702.03037},
year = {2017},
url = {http://arxiv.org/abs/1702.03037},
eprinttype = {arXiv},
eprint = {1702.03037},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LeiboZLMG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HesterVPLSPSDOA17,
author = {Todd Hester and
Matej Vecer{\'{\i}}k and
Olivier Pietquin and
Marc Lanctot and
Tom Schaul and
Bilal Piot and
Andrew Sendonaris and
Gabriel Dulac{-}Arnold and
Ian Osband and
John P. Agapiou and
Joel Z. Leibo and
Audrunas Gruslys},
title = {Learning from Demonstrations for Real World Reinforcement Learning},
journal = {CoRR},
volume = {abs/1704.03732},
year = {2017},
url = {http://arxiv.org/abs/1704.03732},
eprinttype = {arXiv},
eprint = {1704.03732},
timestamp = {Tue, 28 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HesterVPLSPSDOA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SunehagLGCZJLSL17,
author = {Peter Sunehag and
Guy Lever and
Audrunas Gruslys and
Wojciech Marian Czarnecki and
Vin{\'{\i}}cius Flores Zambaldi and
Max Jaderberg and
Marc Lanctot and
Nicolas Sonnerat and
Joel Z. Leibo and
Karl Tuyls and
Thore Graepel},
title = {Value-Decomposition Networks For Cooperative Multi-Agent Learning},
journal = {CoRR},
volume = {abs/1706.05296},
year = {2017},
url = {http://arxiv.org/abs/1706.05296},
eprinttype = {arXiv},
eprint = {1706.05296},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SunehagLGCZJLSL17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-00832,
author = {Marc Lanctot and
Vin{\'{\i}}cius Flores Zambaldi and
Audrunas Gruslys and
Angeliki Lazaridou and
Karl Tuyls and
Julien P{\'{e}}rolat and
David Silver and
Thore Graepel},
title = {A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning},
journal = {CoRR},
volume = {abs/1711.00832},
year = {2017},
url = {http://arxiv.org/abs/1711.00832},
eprinttype = {arXiv},
eprint = {1711.00832},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-00832.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-05074,
author = {Karl Tuyls and
Julien P{\'{e}}rolat and
Marc Lanctot and
Georg Ostrovski and
Rahul Savani and
Joel Z. Leibo and
Toby Ord and
Thore Graepel and
Shane Legg},
title = {Symmetric Decomposition of Asymmetric Games},
journal = {CoRR},
volume = {abs/1711.05074},
year = {2017},
url = {http://arxiv.org/abs/1711.05074},
eprinttype = {arXiv},
eprint = {1711.05074},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-05074.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-01815,
author = {David Silver and
Thomas Hubert and
Julian Schrittwieser and
Ioannis Antonoglou and
Matthew Lai and
Arthur Guez and
Marc Lanctot and
Laurent Sifre and
Dharshan Kumaran and
Thore Graepel and
Timothy P. Lillicrap and
Karen Simonyan and
Demis Hassabis},
title = {Mastering Chess and Shogi by Self-Play with a General Reinforcement
Learning Algorithm},
journal = {CoRR},
volume = {abs/1712.01815},
year = {2017},
url = {http://arxiv.org/abs/1712.01815},
eprinttype = {arXiv},
eprint = {1712.01815},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1712-01815.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ai/BosanskyLLCW16,
author = {Branislav Bosansk{\'{y}} and
Viliam Lis{\'{y}} and
Marc Lanctot and
Jir{\'{\i}} Cerm{\'{a}}k and
Mark H. M. Winands},
title = {Algorithms for computing strategies in two-player simultaneous move
games},
journal = {Artif. Intell.},
volume = {237},
pages = {1--40},
year = {2016},
url = {https://doi.org/10.1016/j.artint.2016.03.005},
doi = {10.1016/J.ARTINT.2016.03.005},
timestamp = {Sun, 02 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ai/BosanskyLLCW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nature/SilverHMGSDSAPL16,
author = {David Silver and
Aja Huang and
Chris J. Maddison and
Arthur Guez and
Laurent Sifre and
George van den Driessche and
Julian Schrittwieser and
Ioannis Antonoglou and
Vedavyas Panneershelvam and
Marc Lanctot and
Sander Dieleman and
Dominik Grewe and
John Nham and
Nal Kalchbrenner and
Ilya Sutskever and
Timothy P. Lillicrap and
Madeleine Leach and
Koray Kavukcuoglu and
Thore Graepel and
Demis Hassabis},
title = {Mastering the game of Go with deep neural networks and tree search},
journal = {Nat.},
volume = {529},
number = {7587},
pages = {484--489},
year = {2016},
url = {https://doi.org/10.1038/nature16961},
doi = {10.1038/NATURE16961},
timestamp = {Mon, 27 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nature/SilverHMGSDSAPL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gecco/FernandoBRBPJLW16,
author = {Chrisantha Fernando and
Dylan Banarse and
Malcolm Reynolds and
Frederic Besse and
David Pfau and
Max Jaderberg and
Marc Lanctot and
Daan Wierstra},
editor = {Tobias Friedrich and
Frank Neumann and
Andrew M. Sutton},
title = {Convolution by Evolution: Differentiable Pattern Producing Networks},
booktitle = {Proceedings of the 2016 on Genetic and Evolutionary Computation Conference,
Denver, CO, USA, July 20 - 24, 2016},
pages = {109--116},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2908812.2908890},
doi = {10.1145/2908812.2908890},
timestamp = {Tue, 06 Nov 2018 11:06:42 +0100},
biburl = {https://dblp.org/rec/conf/gecco/FernandoBRBPJLW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WangSHHLF16,
author = {Ziyu Wang and
Tom Schaul and
Matteo Hessel and
Hado van Hasselt and
Marc Lanctot and
Nando de Freitas},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Dueling Network Architectures for Deep Reinforcement Learning},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {1995--2003},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/wangf16.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/icml/WangSHHLF16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GruslysMDLG16,
author = {Audrunas Gruslys and
R{\'{e}}mi Munos and
Ivo Danihelka and
Marc Lanctot and
Alex Graves},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {Memory-Efficient Backpropagation Through Time},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {4125--4133},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/a501bebf79d570651ff601788ea9d16d-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/GruslysMDLG16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/FernandoBRBPJLW16,
author = {Chrisantha Fernando and
Dylan Banarse and
Malcolm Reynolds and
Frederic Besse and
David Pfau and
Max Jaderberg and
Marc Lanctot and
Daan Wierstra},
title = {Convolution by Evolution: Differentiable Pattern Producing Networks},
journal = {CoRR},
volume = {abs/1606.02580},
year = {2016},
url = {http://arxiv.org/abs/1606.02580},
eprinttype = {arXiv},
eprint = {1606.02580},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/FernandoBRBPJLW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/GruslysMDLG16,
author = {Audrunas Gruslys and
R{\'{e}}mi Munos and
Ivo Danihelka and
Marc Lanctot and
Alex Graves},
title = {Memory-Efficient Backpropagation Through Time},
journal = {CoRR},
volume = {abs/1606.03401},
year = {2016},
url = {http://arxiv.org/abs/1606.03401},
eprinttype = {arXiv},
eprint = {1606.03401},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/GruslysMDLG16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/LisyLB15,
author = {Viliam Lis{\'{y}} and
Marc Lanctot and
Michael H. Bowling},
editor = {Gerhard Weiss and
Pinar Yolum and
Rafael H. Bordini and
Edith Elkind},
title = {Online Monte Carlo Counterfactual Regret Minimization for Search in
Imperfect Information Games},
booktitle = {Proceedings of the 2015 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2015, Istanbul, Turkey, May 4-8, 2015},
pages = {27--36},
publisher = {{ACM}},
year = {2015},
url = {http://dl.acm.org/citation.cfm?id=2772887},
timestamp = {Tue, 08 Mar 2022 10:12:47 +0100},
biburl = {https://dblp.org/rec/conf/atal/LisyLB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/HeinrichLS15,
author = {Johannes Heinrich and
Marc Lanctot and
David Silver},
editor = {Francis R. Bach and
David M. Blei},
title = {Fictitious Self-Play in Extensive-Form Games},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {805--813},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/heinrich15.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/HeinrichLS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangFL15,
author = {Ziyu Wang and
Nando de Freitas and
Marc Lanctot},
title = {Dueling Network Architectures for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1511.06581},
year = {2015},
url = {http://arxiv.org/abs/1511.06581},
eprinttype = {arXiv},
eprint = {1511.06581},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WangFL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tciaig/PepelsWL14,
author = {Tom Pepels and
Mark H. M. Winands and
Marc Lanctot},
title = {Real-Time Monte Carlo Tree Search in Ms Pac-Man},
journal = {{IEEE} Trans. Comput. Intell. {AI} Games},
volume = {6},
number = {3},
pages = {245--257},
year = {2014},
url = {https://doi.org/10.1109/TCIAIG.2013.2291577},
doi = {10.1109/TCIAIG.2013.2291577},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tciaig/PepelsWL14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/Lanctot14,
author = {Marc Lanctot},
editor = {Ana L. C. Bazzan and
Michael N. Huhns and
Alessio Lomuscio and
Paul Scerri},
title = {Further developments of extensive-form replicator dynamics using the
sequence-form representation},
booktitle = {International conference on Autonomous Agents and Multi-Agent Systems,
{AAMAS} '14, Paris, France, May 5-9, 2014},
pages = {1257--1264},
publisher = {{IFAAMAS/ACM}},
year = {2014},
url = {http://dl.acm.org/citation.cfm?id=2617448},
timestamp = {Thu, 25 Sep 2014 07:46:15 +0200},
biburl = {https://dblp.org/rec/conf/atal/Lanctot14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cig/LanctotWPS14,
author = {Marc Lanctot and
Mark H. M. Winands and
Tom Pepels and
Nathan R. Sturtevant},
title = {Monte Carlo Tree Search with heuristic evaluations using implicit
minimax backups},
booktitle = {2014 {IEEE} Conference on Computational Intelligence and Games, {CIG}
2014, Dortmund, Germany, August 26-29, 2014},
pages = {1--8},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/CIG.2014.6932903},
doi = {10.1109/CIG.2014.6932903},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cig/LanctotWPS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cig/TakLW14,
author = {Mandy J. W. Tak and
Marc Lanctot and
Mark H. M. Winands},
title = {Monte Carlo Tree Search variants for simultaneous move games},
booktitle = {2014 {IEEE} Conference on Computational Intelligence and Games, {CIG}
2014, Dortmund, Germany, August 26-29, 2014},
pages = {1--8},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/CIG.2014.6932889},
doi = {10.1109/CIG.2014.6932889},
timestamp = {Fri, 02 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cig/TakLW14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecai/PepelsCWL14,
author = {Tom Pepels and
Tristan Cazenave and
Mark H. M. Winands and
Marc Lanctot},
editor = {Tristan Cazenave and
Mark H. M. Winands and
Yngvi Bj{\"{o}}rnsson},
title = {Minimizing Simple and Cumulative Regret in Monte-Carlo Tree Search},
booktitle = {Computer Games - Third Workshop on Computer Games, {CGW} 2014, Held
in Conjunction with the 21st European Conference on Artificial Intelligence,
{ECAI} 2014, Prague, Czech Republic, August 18, 2014, Revised Selected
Papers},
series = {Communications in Computer and Information Science},
volume = {504},
pages = {1--15},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-319-14923-3\_1},
doi = {10.1007/978-3-319-14923-3\_1},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ecai/PepelsCWL14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecai/PepelsTLW14,
author = {Tom Pepels and
Mandy J. W. Tak and
Marc Lanctot and
Mark H. M. Winands},
editor = {Torsten Schaub and
Gerhard Friedrich and
Barry O'Sullivan},
title = {Quality-based Rewards for Monte-Carlo Tree Search Simulations},
booktitle = {{ECAI} 2014 - 21st European Conference on Artificial Intelligence,
18-22 August 2014, Prague, Czech Republic - Including Prestigious
Applications of Intelligent Systems {(PAIS} 2014)},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {263},
pages = {705--710},
publisher = {{IOS} Press},
year = {2014},
url = {https://doi.org/10.3233/978-1-61499-419-0-705},
doi = {10.3233/978-1-61499-419-0-705},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ecai/PepelsTLW14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PonsenJL14,
author = {Marc J. V. Ponsen and
Steven de Jong and
Marc Lanctot},
title = {Computing Approximate Nash Equilibria and Robust Best-Responses Using
Sampling},
journal = {CoRR},
volume = {abs/1401.4591},
year = {2014},
url = {http://arxiv.org/abs/1401.4591},
eprinttype = {arXiv},
eprint = {1401.4591},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PonsenJL14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LanctotWPS14,
author = {Marc Lanctot and
Mark H. M. Winands and
Tom Pepels and
Nathan R. Sturtevant},
title = {Monte Carlo Tree Search with Heuristic Evaluations using Implicit
Minimax Backups},
journal = {CoRR},
volume = {abs/1406.0486},
year = {2014},
url = {http://arxiv.org/abs/1406.0486},
eprinttype = {arXiv},
eprint = {1406.0486},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LanctotWPS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/icga/LanctotW13,
author = {Marc Lanctot and
Mark H. M. Winands},
title = {{LOA} Wins Lines of Action Tournament},
journal = {J. Int. Comput. Games Assoc.},
volume = {36},
number = {4},
pages = {239--240},
year = {2013},
url = {https://doi.org/10.3233/ICG-2013-36416},
doi = {10.3233/ICG-2013-36416},
timestamp = {Thu, 16 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/icga/LanctotW13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/icga/LanctotW13a,
author = {Marc Lanctot and
Mark H. M. Winands},
title = {{SIA} Wins Surakarta Tournament},
journal = {J. Int. Comput. Games Assoc.},
volume = {36},
number = {4},
pages = {241},
year = {2013},
url = {https://doi.org/10.3233/ICG-2013-36418},
doi = {10.3233/ICG-2013-36418},
timestamp = {Thu, 16 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/icga/LanctotW13a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cg/EsserGWSL13,
author = {Markus Esser and
Michael Gras and
Mark H. M. Winands and
Maarten P. D. Schadd and
Marc Lanctot},
editor = {H. Jaap van den Herik and
Hiroyuki Iida and
Aske Plaat},
title = {Improving Best-Reply Search},
booktitle = {Computers and Games - 8th International Conference, {CG} 2013, Yokohama,
Japan, August 13-15, 2013, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {8427},
pages = {125--137},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-319-09165-5\_11},
doi = {10.1007/978-3-319-09165-5\_11},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cg/EsserGWSL13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eaai/NellerLSA13,
author = {Todd W. Neller and
Marc Lanctot and
Devika Subramanian and
Stephanie E. August},
title = {Model {AI} Assignments 2013},
booktitle = {Fourth Symposium on Education Advances in Artificial Intelligence,
{EAAI} 2013, Bellevue, WA, USA, July 14-18, 2013},
publisher = {{AAAI} Press},
year = {2013},
url = {https://doi.org/10.1609/aaai.v27i3.19009},
doi = {10.1609/AAAI.V27I3.19009},
timestamp = {Thu, 14 Sep 2023 15:28:50 +0200},
biburl = {https://dblp.org/rec/conf/eaai/NellerLSA13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/LanctotLW13,
author = {Marc Lanctot and
Viliam Lis{\'{y}} and
Mark H. M. Winands},
editor = {Tristan Cazenave and
Mark H. M. Winands and
Hiroyuki Iida},
title = {Monte Carlo Tree Search in Simultaneous Move Games with Applications
to Goofspiel},
booktitle = {Computer Games - Workshop on Computer Games, {CGW} 2013, Held in Conjunction
with the 23rd International Conference on Artificial Intelligence,
{IJCAI} 2013, Beijing, China, August 3, 2013, Revised Selected Papers},
series = {Communications in Computer and Information Science},
volume = {408},
pages = {28--43},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-319-05428-5\_3},
doi = {10.1007/978-3-319-05428-5\_3},
timestamp = {Sun, 02 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/LanctotLW13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/LanctotSVAW13,
author = {Marc Lanctot and
Abdallah Saffidine and
Joel Veness and
Christopher Archibald and
Mark H. M. Winands},
editor = {Francesca Rossi},
title = {Monte Carlo *-Minimax Search},
booktitle = {{IJCAI} 2013, Proceedings of the 23rd International Joint Conference
on Artificial Intelligence, Beijing, China, August 3-9, 2013},
pages = {580--586},
publisher = {{IJCAI/AAAI}},
year = {2013},
url = {http://www.aaai.org/ocs/index.php/IJCAI/IJCAI13/paper/view/6862},
timestamp = {Tue, 23 Jan 2024 13:25:46 +0100},
biburl = {https://dblp.org/rec/conf/ijcai/LanctotSVAW13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LisyKLB13,
author = {Viliam Lis{\'{y}} and
Vojtech Kovar{\'{\i}}k and
Marc Lanctot and
Branislav Bosansk{\'{y}}},
editor = {Christopher J. C. Burges and
L{\'{e}}on Bottou and
Zoubin Ghahramani and
Kilian Q. Weinberger},
title = {Convergence of Monte Carlo Tree Search in Simultaneous Move Games},
booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual
Conference on Neural Information Processing Systems 2013. Proceedings
of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States},
pages = {2112--2120},
year = {2013},
url = {https://proceedings.neurips.cc/paper/2013/hash/1579779b98ce9edb98dd85606f2c119d-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/LisyKLB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1304-6057,
author = {Marc Lanctot and
Abdallah Saffidine and
Joel Veness and
Christopher Archibald and
Mark H. M. Winands},
title = {Monte Carlo *-Minimax Search},
journal = {CoRR},
volume = {abs/1304.6057},
year = {2013},
url = {http://arxiv.org/abs/1304.6057},
eprinttype = {arXiv},
eprint = {1304.6057},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1304-6057.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LisyKLB13,
author = {Viliam Lis{\'{y}} and
Vojtech Kovar{\'{\i}}k and
Marc Lanctot and
Branislav Bosansk{\'{y}}},
title = {Convergence of Monte Carlo Tree Search in Simultaneous Move Games},
journal = {CoRR},
volume = {abs/1310.8613},
year = {2013},
url = {http://arxiv.org/abs/1310.8613},
eprinttype = {arXiv},
eprint = {1310.8613},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LisyKLB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/GibsonLBSB12,
author = {Richard G. Gibson and
Marc Lanctot and
Neil Burch and
Duane Szafron and
Michael Bowling},
editor = {J{\"{o}}rg Hoffmann and
Bart Selman},
title = {Generalized Sampling and Variance in Counterfactual Regret Minimization},
booktitle = {Proceedings of the Twenty-Sixth {AAAI} Conference on Artificial Intelligence,
July 22-26, 2012, Toronto, Ontario, Canada},
pages = {1355--1361},
publisher = {{AAAI} Press},
year = {2012},
url = {https://doi.org/10.1609/aaai.v26i1.8241},
doi = {10.1609/AAAI.V26I1.8241},
timestamp = {Mon, 04 Sep 2023 15:56:47 +0200},
biburl = {https://dblp.org/rec/conf/aaai/GibsonLBSB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aamas/JohansonBLGB12,
author = {Michael Johanson and
Nolan Bard and
Marc Lanctot and
Richard G. Gibson and
Michael Bowling},
editor = {Wiebe van der Hoek and
Lin Padgham and
Vincent Conitzer and
Michael Winikoff},
title = {Efficient Nash equilibrium approximation through Monte Carlo counterfactual
regret minimization},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems,
{AAMAS} 2012, Valencia, Spain, June 4-8, 2012 {(3} Volumes)},
pages = {837--846},
publisher = {{IFAAMAS}},
year = {2012},
url = {http://dl.acm.org/citation.cfm?id=2343816},
timestamp = {Thu, 19 Mar 2015 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aamas/JohansonBLGB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LanctotGBB12,
author = {Marc Lanctot and
Richard G. Gibson and
Neil Burch and
Michael Bowling},
title = {No-Regret Learning in Extensive-Form Games with Imperfect Recall},
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/58.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/LanctotGBB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GibsonBLS12,
author = {Richard G. Gibson and
Neil Burch and
Marc Lanctot and
Duane Szafron},
editor = {Peter L. Bartlett and
Fernando C. N. Pereira and
Christopher J. C. Burges and
L{\'{e}}on Bottou and
Kilian Q. Weinberger},
title = {Efficient Monte Carlo Counterfactual Regret Minimization in Games
with Many Player Actions},
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 = {1889--1897},
year = {2012},
url = {https://proceedings.neurips.cc/paper/2012/hash/3df1d4b96d8976ff5986393e8767f5b2-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/GibsonBLS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1205-0622,
author = {Marc Lanctot and
Richard G. Gibson and
Neil Burch and
Martin Zinkevich and
Michael H. Bowling},
title = {No-Regret Learning in Extensive-Form Games with Imperfect Recall},
journal = {CoRR},
volume = {abs/1205.0622},
year = {2012},
url = {http://arxiv.org/abs/1205.0622},
eprinttype = {arXiv},
eprint = {1205.0622},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1205-0622.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/PonsenJL11,
author = {Marc J. V. Ponsen and
Steven de Jong and
Marc Lanctot},
title = {Computing Approximate Nash Equilibria and Robust Best-Responses Using
Sampling},
journal = {J. Artif. Intell. Res.},
volume = {42},
pages = {575--605},
year = {2011},
url = {https://doi.org/10.1613/jair.3402},
doi = {10.1613/JAIR.3402},
timestamp = {Mon, 21 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jair/PonsenJL11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/VenessLB11,
author = {Joel Veness and
Marc Lanctot and
Michael H. Bowling},
editor = {John Shawe{-}Taylor and
Richard S. Zemel and
Peter L. Bartlett and
Fernando C. N. Pereira and
Kilian Q. Weinberger},
title = {Variance Reduction in Monte-Carlo Tree Search},
booktitle = {Advances in Neural Information Processing Systems 24: 25th Annual
Conference on Neural Information Processing Systems 2011. Proceedings
of a meeting held 12-14 December 2011, Granada, Spain},
pages = {1836--1844},
year = {2011},
url = {https://proceedings.neurips.cc/paper/2011/hash/d736bb10d83a904aefc1d6ce93dc54b8-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/VenessLB11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/PonsenLJ10,
author = {Marc J. V. Ponsen and
Marc Lanctot and
Steven de Jong},
title = {{MCRNR:} Fast Computing of Restricted Nash Responses by Means of Sampling},
booktitle = {Interactive Decision Theory and Game Theory, Papers from the 2010
{AAAI} Workshop, Atlanta, Georgia, USA, July 12, 2010},
series = {{AAAI} Technical Report},
volume = {{WS-10-03}},
publisher = {{AAAI}},
year = {2010},
url = {http://aaai.org/ocs/index.php/WS/AAAIW10/paper/view/1985},
timestamp = {Tue, 05 Sep 2023 08:59:27 +0200},
biburl = {https://dblp.org/rec/conf/aaai/PonsenLJ10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LanctotWZB09,
author = {Marc Lanctot and
Kevin Waugh and
Martin Zinkevich and
Michael H. Bowling},
editor = {Yoshua Bengio and
Dale Schuurmans and
John D. Lafferty and
Christopher K. I. Williams and
Aron Culotta},
title = {Monte Carlo Sampling for Regret Minimization in Extensive Games},
booktitle = {Advances in Neural Information Processing Systems 22: 23rd Annual
Conference on Neural Information Processing Systems 2009. Proceedings
of a meeting held 7-10 December 2009, Vancouver, British Columbia,
Canada},
pages = {1078--1086},
publisher = {Curran Associates, Inc.},
year = {2009},
url = {https://proceedings.neurips.cc/paper/2009/hash/00411460f7c92d2124a67ea0f4cb5f85-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/LanctotWZB09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cig/SailerBL07,
author = {Franisek Sailer and
Michael Buro and
Marc Lanctot},
title = {Adversarial Planning Through Strategy Simulation},
booktitle = {Proceedings of the 2007 {IEEE} Symposium on Computational Intelligence
and Games, {CIG} 2007, Honolulu, Hawaii, USA, 1-5 April, 2007},
pages = {80--87},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/CIG.2007.368082},
doi = {10.1109/CIG.2007.368082},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/cig/SailerBL07.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 16:53 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:
