Multiagent reinforcement learning: algorithm converging to Nash equilibrium in general-sum discounted stochastic games

This paper introduces a multiagent reinforcement learning algorithm that converges with a given accuracy to stationary Nash equilibria in general-sum discounted stochastic games. Under some assumptions we formally prove its convergence to Nash equilibrium in self-play. We claim that it is the first algorithm that converges to stationary Nash equilibrium in the general case. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learning; I.2.11 [Artificial Intelligence]: Distributed Artificial Intelligence—Multiagent systems General Terms Algorithms, Theory Keywords algorithmic game theory, stochastic games, computation of equilibria, multiagent reinforcement learning

• Type: Conference
• Year: 2009
• Where: ATAL
• Authors: Natalia Akchurina
• Keywords: Artificial Intelligence, ATAL 2009, Multiagent Reinforcement, Nash Equilibrium, Stationary Nash Equilibria