@article{Bard19Hanabi,
title = {The {Hanabi} challenge: A new frontier for AI research},
journal = {Artificial Intelligence},
volume = {280},
year = {2020},
url = {http://www.sciencedirect.com/science/article/pii/S0004370219300116},
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},
}
@article{Tuyls19EGTA,
Author = {Tuyls, Karl and Perolat, Julien and Lanctot, Marc and Hughes, Edward and Everett, Richard and Leibo, Joel Z. and Szepesv{\'a}ri, Csaba and Graepel, Thore},
Journal = {Autonomous Agents and Multi-Agent Systems},
Number = {1},
Pages = {7},
Title = {Bounds and dynamics for empirical game theoretic analysis},
Url = {https://doi.org/10.1007/s10458-019-09432-y},
Volume = {34},
Year = {2019},
}
@article{Omidshafiei19AlphaRank,
Author = {Omidshafiei, Shayegan and Papadimitriou, Christos and Piliouras, Georgios and Tuyls, Karl and Rowland, Mark and Lespiau, Jean-Baptiste and Czarnecki, Wojciech M. and Lanctot, Marc and Perolat, Julien and Munos, Remi},
Journal = {Scientific Reports},
Number = {1},
Pages = {9937},
Title = {α-Rank: Multi-Agent Evaluation by Evolution},
Url = {https://doi.org/10.1038/s41598-019-45619-9},
Volume = {9},
Year = {2019}
}
@article{Silver18AlphaZero,
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 Lillicrap and Karen Simonyan and Demis Hassabis},
title = {A general reinforcement learning algorithm that masters chess, shogi, and {G}o through self-play},
journal = {Science},
volume = 632,
number = 6419,
pages = {1140--1144},
year = 2018
}
@article{Tuyls17Symmetric,
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 = {Nature Scientific Reports},
volume = 8,
number = 1,
pages = {1--15},
year = 2017
}
@article{Bosansky16Algorithms,
author = {Branislav Bo\v{s}ansk\'{y} and Viliam Lis\'{y} and Marc Lanctot and Ji\v{r}\'{i} \v{C}erm\'{a}k and Mark H.M. Winands},
title = {Algorithms for computing strategies in two-player simultaneous move games},
journal = {Artificial Intelligence},
volume = 237,
pages = {1--40},
year = 2016
}
@article{Silver16Go,
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 Veda Panneershelvam and Marc Lanctot and Sander Dieleman and Dominik Grewe and John Nham and Nal Kalchbrenner and Ilya Sutskever and Timothy Lillicrap and Madeleine Leach and Koray Kavukcuoglu and Thore Graepel and Demis Hassabis},
title = {Mastering the Game of {G}o with Deep Neural Networks and Tree Search},
journal = {Nature},
volume = 529,
pages = {484--489},
year = 2016
}
@article{Pepels14MsPacMan,
author = {Tom Pepels and Mark H.M. Winands and Marc Lanctot},
title = {Real-time {M}onte {C}arlo Tree Search for {M}s {P}ac-{M}an},
journal = {IEEE Transactions on Computational Intelligence and AI in Games},
volume = 6,
number = 3,
pages = {245--257},
year = 2014
}
@article{Ponsen11Computing,
author = {Marc Ponsen and Steven de Jong and Marc Lanctot},
title = {Computing Approximate {N}ash Equilibria and Robust Best-Responses Using Sampling},
journal = {Journal of Artificial Intelligence Research},
volume = 42,
pages = {575--605},
year = 2011
}
@inbook{sailer08simulation,
author = {M. Buro and M. Lanctot and F. Sailer},
title = {Simulation-Based Planning in {RTS} Games},
booktitle = {{AI} Game Programming Wisdom 4},
publisher = {Charles River Media},
year = 2008,
pages = {405--418}
}
Conference Papers
@inproceedings{Schmid19VRMCCFR,
title = {Variance Reduction in Monte Carlo Counterfactual Regret Minimization ({VR-MCCFR}) for Extensive Form Games using Baselines},
author = {Martin Schmid and Neil Burch and Marc Lanctot and Matej Moravcik and Rudolf Kadlec and Michael Bowling},
booktitle = {Proceedings of the The Thirty-Third AAAI Conference on Artificial Intelligence},
year = {2019},
}
@inproceedings{Srinivasan18RPG,
title = {Actor-Critic Policy Optimization in Partially Observable Multiagent Environments},
author = {Sriram Srinivasan and Marc Lanctot and Vinicius Zambaldi and Julien P\'{e}rolat and Karl Tuyls and R\'{e}mi Munos and Michael Bowling},
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
year = {2018},
}
@inproceedings{Cao18Emergent,
title = {Emergent Communication through Negotiation},
author = {Kris Cao and Angeliki Lazaridou and Marc Lanctot and Joel Z. Leibo and Karl Tuyls and Stephen Clark},
booktitle = {Proceedings of the Sixth International Conference on Learning Representations (ICLR)},
year = {2018},
}
@inproceedings{Tuyls18Generalized,,
title = {A Generalized Method for Empirical Game Theoretic Analysis},
author = {Karl Tuyls and Julien Perolat and Marc Lanctot and Joel Z. Leibo and Thore Graepel},
booktitle = {Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
year = {2018},
}
@inproceedings{Hester18DQFD,
title = {Deep Q-learning from Demonstrations},
author = {Todd Hester and Matej Vecerik and Olivier Pietquin and Marc Lanctot and Tom Schaul and Bilal Piot and Dan Horgan and John Quan and Andrew Sendonaris and Gabriel Dulac-Arnold and Ian Osband and John Agapiou and Joel Z. Leibo and Audrunas Gruslys},
booktitle = {Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
year = {2018},
}
@inproceedings{Lanctot17PSRO,
title = {A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning},
author = {Marc Lanctot and Vinicius Zambaldi and Audrunas Gruslys and Angeliki Lazaridou and Karl Tuyls and Julien Perolat and David Silver and Thore Graepel},
booktitle = {Advances in Neural Information Processing Systems},
year = {2017},
}
@inproceedings{Leibo17SSD,
title = {Multi-agent Reinforcement Learning in Sequential Social Dilemmas},
author = {Joel Z. Leibo and Vinicius Zambaldi and Marc Lanctot and Janusz Marecki and Thore Graepel},
booktitle = {Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
year = {2017},
}
@inproceedings{Wang16Dueling,
title = {Dueling Network Architectures for Deep Reinforcement Learning},
author = {Ziyu Wang and Tom Schaul and Matteo Hessel and Hado van Hasselt and Marc Lanctot and Nando de Freitas},
booktitle = {Proceedings of the International Conference on Machine Learning (ICML)},
year = {2016},
pages = {1995--2003},
}
@inproceedings{Fernando16DPPN,
title = {Convolution by Evolution: Differentiable Pattern Producing Networks},
author = {Chrisantha Fernando and Dylan Banarse and Malcolm Reynolds and Frederic Besse and David Pfau and Max Jaderberg and Marc Lanctot and Daan Wierstra},
booktitle = {Proceedings of The Genetic and Evolutionary Computation Conference (GECCO)},
year = {2016},
% pages = {not yet available},
}
@inproceedings{Heinrich15FSP,
title = {Fictitious Self-Play in Extensive-Form Games},
author = {Johannes Heinrich and Marc Lanctot and David Silver},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning ({ICML} 2015)},
year = {2015},
% pages = {not yet available},
}
@inproceedings{Lisy15Online,
title = {Online {M}onte {C}arlo Counterfactual Regret Minimization for Search in Imperfect Information Games},
author = {Viliam Lis\'{y} and Marc Lanctot and Michael Bowling},
booktitle = {Proceedings of the Fourteenth International Conference on Autonomous Agents and Multi-Agent Systems ({AAMAS})},
year = {2015},
pages = {27--36},
AcceptNumbers = {167 of 670},
AcceptRate = {24.9%}
}
@inproceedings{Tak14smmctsggp,
author = {Mandy J.W. Tak and Marc Lanctot and Mark H.M. Winands},
title = {{M}onte {C}arlo Tree Search Variants for Simultaneous Move Games},
booktitle = {Proceedings of the IEEE Conference on Computational Intelligence and Games ({CIG})},
year = 2014,
pages = {232--239}
}
@inproceedings{Lanctot14Implicit,
author = {Marc Lanctot and Mark H.M. Winands and Tom Pepels and Nathan R. Sturtevant},
title = {{M}onte {C}arlo Tree Search with Heuristic Evaluations using Implicit Minimax Backups},
booktitle = {Proceedings of the IEEE Conference on Computational Intelligence and Games ({CIG})},
year = 2014,
pages = {341--348}
}
@inproceedings{Pepels14Quality,
title = {Quality-based Rewards for {M}onte-{C}arlo Tree Search Simulations},
author = {Tom Pepels and Mandy J.W. Tak and Marc Lanctot and Mark H.M. Winands},
booktitle = {Proceedings of the 21st European Conference on Artificial Intelligence ({ECAI})},
year = {2014},
% pages not yet available
AcceptNumbers = {158 of 562},
AcceptRate = {28.1\%}
}
@inproceedings{Lanctot14Further,
title = {Further Developments of Extensive-Form Replicator Dynamics using the Sequence-Form Representation},
author = {Marc Lanctot},
booktitle = {Proceedings of the Thirteenth International Conference on Autonomous Agents and Multi-Agent Systems ({AAMAS})},
year = {2014},
pages = {1257--1264},
AcceptNumbers = {169 of 709},
AcceptRate = {23.8\%}
}
@inproceedings{Lanctot13Tron,
title = {{M}onte {C}arlo Tree Search for Simultaneous Move Games: A Case Study in the Game of {T}ron},
author = {Marc Lanctot and Christopher Wittlinger and Mark H.M. Winands and Niek G.P. Den Teuling},
booktitle = {Proceedings of the Twenty-Fifth Benelux Conference on Artificial Intelligence ({BNAIC})},
year = {2013},
pages = {104--111}
}
@inproceedings{Lisy13Computing,
author = {Viliam Lisy and Vojtech Kovarik and Marc Lanctot and Branislav Bosansky},
title = {Convergence of {M}onte {C}arlo Tree Search in Simultaneous Move Games},
booktitle = {Advances in Neural Information Processing Systems 26},
year = {2013},
pages = {2112--2120},
}
@inproceedings{Esser14Improving,
title = {Improving Best-Reply Search},
author = {Markus Esser and Michael Gras and Mark H.M. Winands and Maarten P.D. Schadd and Marc Lanctot},
booktitle = {8th International Conference on Computers and Games ({CG} 2013)},
year = {2014},
series = {LNCS},
volume = {8427},
pages = {125--137}
}
@inproceedings{Lanctot13MCMS,
title = {{M}onte {C}arlo *-Minimax Search},
author = {Marc Lanctot and Abdallah Saffidine and Joel Veness and Chris Archibald and Mark H.M. Winands},
booktitle = {Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence ({IJCAI})},
year = {2013},
pages = {580--586},
AcceptNumbers = {413 of 1473},
AcceptRate = {28\%}
}
@inproceedings{Gibson12AS,
title = {Efficient {M}onte {C}arlo Counterfactual Regret Minimization in Games with Many Player Actions},
author = {Richard Gibson and Neil Burch and Marc Lanctot and Duane Szafron},
booktitle = {Advances in Neural Information Processing Systems 25},
year = 2012
AcceptNumbers = {370 of 1467},
AcceptRate = {25.2\%}
}
@inproceedings{Lanctot12IR,
title = {No-Regret Learning in Extensive-Form Games with Imperfect Recall},
author = {Marc Lanctot and Richard Gibson and Neil Burch and Michael Bowling},
booktitle = {Proceedings of the Twenty-Ninth International Conference on Machine Learning ({ICML} 2012)},
year = {2012},
AcceptNumbers = {243 of 890},
AcceptRate = {27.3\%}
}
@inproceedings{Gibson12probing,
title = {Generalized Sampling and Variance in Counterfactual Regret Minimization},
author = {Richard Gibson and Marc Lanctot and Neil Burch and Duane Szafron and Michael Bowling},
booktitle = {Proceedings of the Twenty-Sixth Conference on Artificial Intelligence (AAAI-12).},
pages = {1355--1361},
year = {2012},
AcceptNumbers = {294 of 1129},
AcceptRate = {26\%}
}
@InProceedings(12aamas-pcs,
Title = {Efficient Nash Equilibrium Approximation through {M}onte {C}arlo Counterfactual Regret Minimization},
Author = {Michael Johanson and Nolan Bard and Marc Lanctot and Richard Gibson and Michael Bowling},
Booktitle = {Proceedings of the Eleventh International Conference on Autonomous Agents and Multi-Agent Systems ({AAMAS})},
Year = {2012},
AcceptNumbers = {137 of 671},
AcceptRate = {20\%}
)
@inproceedings{Veness11variance,
title = {Variance Reduction in {M}onte-{C}arlo Tree Search},
author = {Joel Veness and Marc Lanctot and Michael Bowling},
booktitle = {Advances in Neural Information Processing Systems 24},
editor = {J. Shawe-Taylor and R.S. Zemel and P. Bartlett and F. Pereira and K.Q. Weinberger},
year = {2011},
pages = {1836--1844},
AcceptRate = {22\%},
AcceptNumbers = {305 of 1400}
}
@inproceedings{Lanctot09mccfr,
title = {{M}onte {C}arlo Sampling for Regret Minimization in Extensive Games},
author = {Marc Lanctot and Kevin Waugh and Martin Zinkevich and Michael Bowling},
booktitle = {Advances in Neural Information Processing Systems 22},
editor = {Y. Bengio and D. Schuurmans and J. Lafferty and C. K. I. Williams and A. Culotta},
pages = {1078--1086},
year = {2009},
AcceptRate = {24\%},
AcceptNumbers = {263 of 1105}
}
@inproceedings{Lanctot06pathfinding,
author = {M. Lanctot and N. NgManSun and C. Verbrugge},
title = {Path-finding for Large Scale Multi-player Games},
booktitle = {Proceedings of The 2nd Annual North-American {GAME-ON} Conference ({GAME-ON'NA} 2005) North-America},
year = 2006,
pages = {26--33},
publisher = {Eurosis}
}
@inproceedings{Lanctot04locally,
author = {Marc Lanctot and Clark Verbrugge},
title = {Locally-Adaptive Virtual Environments in Persistent-State Multi-Player Games},
booktitle = {Proceedings of The 5th Annual European {GAME-ON} Conference ({GAME-ON} 2004)},
year = 2004,
pages = {89--96},
publisher = {Eurosis}
}
Refereed Workshop & Symposia Papers, Extended Abstracts
@incollection{Pepels14hmcts,
author = {Tom Pepels and Tristan Cazenave and Mark H.M. Winands and Marc Lanctot},
title = {Minimizing Simple and Cumulative Regret in {M}onte-{C}arlo Tree Search},
series = {Communications in Computer and Information Science},
booktitle = {Computer Games},
publisher = {Springer},
volume = {504},
pages = {1--15},
year = 2014
}
@incollection{Lanctot13smmcts,
author = {Marc Lanctot and Viliam Lis\'{y} and Mark H.M. Winands},
title = {{M}onte {C}arlo Tree Search in Simultaneous Move Games with Applications to {G}oofspiel},
series = {Communications in Computer and Information Science},
booktitle = {Computer Games},
publisher = {Springer},
volume = 408,
pages = {28--43},
year = 2014
}
@inproceedings{Neller13cfrnotes,
title = {An Introduction to Counterfactual Regret Minimization},
author = {Todd W. Neller and Marc Lanctot},
booktitle = {Proceedings of Model {AI} Assignments, The Fourth Symposium on Educational Advances in Artificial Intelligence ({EAAI}-2013)},
year = 2013,
note = {\url{http://modelai.gettysburg.edu/2013/cfr/index.html}},
}
Preprints
@article{Lanctot2019OpenSpiel,
title = {{OpenSpiel}: A Framework for Reinforcement Learning in Games},
author = {Marc Lanctot and Edward Lockhart and Jean-Baptiste Lespiau and Vinicius 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 Kramár and Bart De Vylder and Brennan Saeta and
James Bradbury and David Ding and Sebastian Borgeaud and Matthew Lai and Julian Schrittwieser and
Thomas Anthony and Edward Hughes and Ivo Danihelka and Jonah Ryan-Davis},
year = {2019},
eprint = {1908.09453},
archivePrefix = {arXiv},
primaryClass = {cs.LG},
journal = {CoRR},
volume = {abs/1908.09453},
url = {http://arxiv.org/abs/1908.09453},
note = {\url{http://arxiv.org/abs/1908.09453}},
}
Theses
@phdthesis{Lanctot13phdthesis,
author = {Marc Lanctot},
title = {{M}onte {C}arlo Sampling and Regret Minimization for Equilibrium Computation and Decision-Making in Large Extensive Form Games},
year = 2013,
school = {University of Alberta},
month = {June},
address = {University of Alberta, Computing Science, 116 St. and 85 Ave., Edmonton, Alberta {T6G 2R3}}
}
@mastersthesis{Lanctot05thesis,
author = {Marc Lanctot},
title = {{Adaptive Virtual Environments in Modern Multi-Player Computer Games}}
school = {McGill University}
address = {3480 University Street, McConnell Engineering Building, Room 318, Montreal, Quebec, Canada, {H3A 2A7}},
year = 2005,
month = {May},
}