An Analysis of Stochastic Game Theory for Multiagent Reinforcement Learning
- Michael Bowling, University of Alberta
- Manuela Veloso
Learning behaviors in a multiagent environment is crucial for developing and adapting multiagent systems. Reinforcement learning techniques have addressed this problem for a single agent acting in a stationary environment, which is modeled as a Markov decision process (MDP). But, multiagent environments are inherently non-stationary since the other agents are free to change their behavior as they also learn and adapt. Stochastic games, first studied in the game theory community, are a natural extension of MDPs to include multiple agents. In this paper we contribute a comprehensive presentation of the relevant techniques for solving stochastic games from both the game theory community and reinforcement learning communities. We examine the assumptions and limitations of these algorithms, and identify similarities between these algorithms, single agent reinforcement learners, and basic game theory techniques.
Citation
M. Bowling, M. Veloso. "An Analysis of Stochastic Game Theory for Multiagent Reinforcement Learning". Technical Report, Carnegie Mellon University, (CMU-CS-00-165), January 2000.| Keywords: | machine learning |
| Category: | Technical Report |
BibTeX
@manual{Bowling+Veloso:00,
author = {Michael Bowling and Manuela Veloso},
title = {An Analysis of Stochastic Game Theory for Multiagent Reinforcement
Learning},
Institution = {Carnegie Mellon University},
Number = "CMU-CS-00-165",
year = 2000,
}Last Updated: March 12, 2007Submitted by Nelson Loyola
