论文信息 - Learning to Coordinate Efficiently: A Model-based Approach

Learning to Coordinate Efficiently: A Model-based Approach

In common-interest stochastic games all players receive an identical payoff. Players participating in such games must learn to coordinate with each other in order to receive the highest-possible value. A number of reinforcement learning algorithms have been proposed for this problem, and some have been shown to converge to good solutions in the limit. In this paper we show that using very simple model-based algorithms, much better (i.e., polynomial) convergence rates can be attained. Moreover, our model-based algorithms are guaranteed to converge to the optimal value, unlike many of the existing algorithms.

Moshe Tennenholtz | R. Brafman

[1] Ronen I. Brafman,et al. R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning , 2001, J. Mach. Learn. Res..

[2] Manuela M. Veloso,et al. Rational and Convergent Learning in Stochastic Games , 2001, IJCAI.

[3] Michael L. Littman,et al. Friend-or-Foe Q-learning in General-Sum Games , 2001, ICML.

[4] Michael Kearns,et al. Near-Optimal Reinforcement Learning in Polynomial Time , 2002, Machine Learning.

[5] Michael P. Wellman,et al. Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm , 1998, ICML.

[6] Craig Boutilier,et al. The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems , 1998, AAAI/IAAI.

[7] Michael L. Littman,et al. Markov Games as a Framework for Multi-Agent Reinforcement Learning , 1994, ICML.

[8] L. Shapley,et al. Stochastic Games* , 1953, Proceedings of the National Academy of Sciences.

[9] Xiaofeng Wang,et al. Reinforcement Learning to Play an Optimal Nash Equilibrium in Team Markov Games , 2002, NIPS.

[10] R. Karp,et al. On Nonterminating Stochastic Games , 1966 .