Reinforcement Learning for Stochastic Cooperative Multi-Agent Systems

Martin Lauer; Martin Riedmiller

doi:10.1109/AAMAS.2004.10253

Previous
Next
Table of Contents

Autonomous Agents and Multiagent Systems, International Joint Conference on

Reinforcement Learning for Stochastic Cooperative Multi-Agent Systems

Year: 2004, Volume: 4, Pages: 1516-1517

DOI Bookmark: 10.1109/AAMAS.2004.10253

Authors

Martin Lauer, University of Osnabrück
Martin Riedmiller, University of Osnabrück

Abstract

We present a distributed variant of Q-learning that allows to learn the optimal cost-to-go function in stochastic cooperative multi-agent domains without communication between the agents.