An experimental study of different approaches to reinforcement learning in common interest stochastic games

Avi Bab, Ronen Brafman

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

Stochastic (a.k.a. Markov) Games pose many unsolved problems in Game Theory. One class of stochastic games that is better understood is that of Common Interest Stochastic Games (CISG). CISGs form an interesting class of multi-agent settings where the distributed nature of the systems, rather than adverserial behavior, is the main challenge to efficient learning. In this paper we examine three different approaches to RL in CISGs, embedded in the FriendQ, OAL, and Rmax algorithms. We show the performance of the above algorithms on some non-trivial games that illustrate the advantages and disadvantages of the different approaches.

Original languageEnglish
Pages (from-to)75-86
Number of pages12
JournalLecture Notes in Computer Science
Volume3201
DOIs
StatePublished - 1 Jan 2004
Event15th European Conference on Machine Learning, ECML 2004 - Pisa, Italy
Duration: 20 Sep 200424 Sep 2004

Fingerprint

Dive into the research topics of 'An experimental study of different approaches to reinforcement learning in common interest stochastic games'. Together they form a unique fingerprint.

Cite this