Zobrazeno 1 - 10
of 83
pro vyhledávání: '"Panageas, Ioannis"'
We study the problem of learning a Nash equilibrium (NE) in Markov games which is a cornerstone in multi-agent reinforcement learning (MARL). In particular, we focus on infinite-horizon adversarial team Markov games (ATMGs) in which agents that share
Externí odkaz:
http://arxiv.org/abs/2410.05673
Last-iterate behaviors of learning algorithms in repeated two-player zero-sum games have been extensively studied due to their wide applications in machine learning and related tasks. Typical algorithms that exhibit the last-iterate convergence prope
Externí odkaz:
http://arxiv.org/abs/2406.10605
We consider the problem of computing Nash equilibria in potential games where each player's strategy set is subject to private uncoupled constraints. This scenario is frequently encountered in real-world applications like road network congestion game
Externí odkaz:
http://arxiv.org/abs/2402.07797
Policy gradient methods enjoy strong practical performance in numerous tasks in reinforcement learning. Their theoretical understanding in multiagent settings, however, remains limited, especially beyond two-player competitive and potential Markov ga
Externí odkaz:
http://arxiv.org/abs/2312.12067
Last-iterate convergence has received extensive study in two player zero-sum games starting from bilinear, convex-concave up to settings that satisfy the MVI condition. Typical methods that exhibit last-iterate convergence for the aforementioned game
Externí odkaz:
http://arxiv.org/abs/2310.02604
Fictitious Play (FP) is a simple and natural dynamic for repeated play with many applications in game theory and multi-agent reinforcement learning. It was introduced by Brown (1949,1951) and its convergence properties for two-player zero-sum games w
Externí odkaz:
http://arxiv.org/abs/2310.02387
In this work, we introduce a new variant of online gradient descent, which provably converges to Nash Equilibria and simultaneously attains sublinear regret for the class of congestion games in the semi-bandit feedback setting. Our proposed method ad
Externí odkaz:
http://arxiv.org/abs/2306.15543
Autor:
Kalogiannis, Fivos, Panageas, Ioannis
The works of (Daskalakis et al., 2009, 2022; Jin et al., 2022; Deng et al., 2023) indicate that computing Nash equilibria in multi-player Markov games is a computationally hard task. This fact raises the question of whether or not computational intra
Externí odkaz:
http://arxiv.org/abs/2305.14329
Most of the literature on learning in games has focused on the restrictive setting where the underlying repeated game does not change over time. Much less is known about the convergence of no-regret learning algorithms in dynamic multiagent settings.
Externí odkaz:
http://arxiv.org/abs/2301.11241
Autor:
Anagnostides, Ioannis, Kalogiannis, Fivos, Panageas, Ioannis, Vlatakis-Gkaragkounis, Emmanouil-Vasileios, McAleer, Stephen
Adversarial team games model multiplayer strategic interactions in which a team of identically-interested players is competing against an adversarial player in a zero-sum game. Such games capture many well-studied settings in game theory, such as con
Externí odkaz:
http://arxiv.org/abs/2301.02129