Zobrazeno 1 - 10
of 154
pro vyhledávání: '"Lanctot, Marc"'
We propose ABCs (Adaptive Branching through Child stationarity), a best-of-both-worlds algorithm combining Boltzmann Q-learning (BQL), a classic reinforcement learning algorithm for single-agent domains, and counterfactual regret minimization (CFR),
Externí odkaz:
http://arxiv.org/abs/2402.11835
Autor:
Gemp, Ian, Lanctot, Marc, Marris, Luke, Mao, Yiran, Duéñez-Guzmán, Edgar, Perrin, Sarah, Gyorgy, Andras, Elie, Romuald, Piliouras, Georgios, Kaisers, Michael, Hennes, Daniel, Bullard, Kalesha, Larson, Kate, Bachrach, Yoram
The core is a central solution concept in cooperative game theory, defined as the set of feasible allocations or payments such that no subset of agents has incentive to break away and form their own subgroup or coalition. However, it has long been kn
Externí odkaz:
http://arxiv.org/abs/2402.03928
Autor:
Gemp, Ian, Bachrach, Yoram, Lanctot, Marc, Patel, Roma, Dasagi, Vibhavari, Marris, Luke, Piliouras, Georgios, Liu, Siqi, Tuyls, Karl
Game theory is the study of mathematical models of strategic interactions among rational agents. Language is a key medium of interaction for humans, though it has historically proven difficult to model dialogue and its strategic motivations mathemati
Externí odkaz:
http://arxiv.org/abs/2402.01704
We study computationally efficient methods for finding equilibria in n-player general-sum games, specifically ones that afford complex visuomotor skills. We show how existing methods would struggle in this setting, either computationally or in theory
Externí odkaz:
http://arxiv.org/abs/2401.05133
Autor:
Lanctot, Marc, Larson, Kate, Bachrach, Yoram, Marris, Luke, Li, Zun, Bhoopchand, Avishkar, Anthony, Thomas, Tanner, Brian, Koop, Anna
We argue that many general evaluation problems can be viewed through the lens of voting theory. Each task is interpreted as a separate voter, which requires only ordinal rankings or pairwise comparisons of agents to produce an overall evaluation. By
Externí odkaz:
http://arxiv.org/abs/2312.03121
Autor:
Lanctot, Marc, Schultz, John, Burch, Neil, Smith, Max Olan, Hennes, Daniel, Anthony, Thomas, Perolat, Julien
Progress in fields of machine learning and adversarial planning has benefited significantly from benchmark domains, from checkers and the classic UCI data sets to Go and Diplomacy. In sequential decision-making, agent evaluation has largely been rest
Externí odkaz:
http://arxiv.org/abs/2303.03196
Autor:
Sychrovský, David, Šustr, Michal, Davoodi, Elnaz, Bowling, Michael, Lanctot, Marc, Schmid, Martin
The literature on game-theoretic equilibrium finding predominantly focuses on single games or their repeated play. Nevertheless, numerous real-world scenarios feature playing a game sampled from a distribution of similar, but not identical games, suc
Externí odkaz:
http://arxiv.org/abs/2303.01074
Autor:
Li, Zun, Lanctot, Marc, McKee, Kevin R., Marris, Luke, Gemp, Ian, Hennes, Daniel, Muller, Paul, Larson, Kate, Bachrach, Yoram, Wellman, Michael P.
Multiagent reinforcement learning (MARL) has benefited significantly from population-based and game-theoretic training regimes. One approach, Policy-Space Response Oracles (PSRO), employs standard reinforcement learning to compute response policies v
Externí odkaz:
http://arxiv.org/abs/2302.00797
Autor:
Marris, Luke, Lanctot, Marc, Gemp, Ian, Omidshafiei, Shayegan, McAleer, Stephen, Connor, Jerome, Tuyls, Karl, Graepel, Thore
Rating strategies in a game is an important area of research in game theory and artificial intelligence, and can be applied to any real-world competitive or cooperative setting. Traditionally, only transitive dependencies between strategies have been
Externí odkaz:
http://arxiv.org/abs/2210.02205
Autor:
Gemp, Ian, Anthony, Thomas, Bachrach, Yoram, Bhoopchand, Avishkar, Bullard, Kalesha, Connor, Jerome, Dasagi, Vibhavari, De Vylder, Bart, Duenez-Guzman, Edgar, Elie, Romuald, Everett, Richard, Hennes, Daniel, Hughes, Edward, Khan, Mina, Lanctot, Marc, Larson, Kate, Lever, Guy, Liu, Siqi, Marris, Luke, McKee, Kevin R., Muller, Paul, Perolat, Julien, Strub, Florian, Tacchetti, Andrea, Tarassov, Eugene, Wang, Zhe, Tuyls, Karl
The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and training 3-d hu
Externí odkaz:
http://arxiv.org/abs/2209.10958