Please use this identifier to cite or link to this item:
Title: Extended Replicator Dynamics as a Key to Reinforcement Learning in Multi-agent Systems
Authors: TUYLS, Karl 
Heytens, Dries
Nowé, Ann
Manderick, Bernard
Issue Date: 2003
Source: MACHINE LEARNING: ECML 2003. p. 421-431
Series/Report: Lecture Notes in Computer Science
Series/Report no.: 2837
Abstract: Modeling learning agents in the context of Multi-agent Systems requires an adequate understanding of their dynamic behaviour. Evolutionary Game Theory provides a dynamics which describes how strategies evolve over time. Börgers et al. and Tuyls et al. have shown how classical Reinforcement Learning (RL) techniques such as Cross-learning and Q-learning relate to the Replicator Dynamics (RD). This provides a better understanding of the learning process. In this paper, we introduce an extension of the Replicator Dynamics from Evolutionary Game Theory. Based on this new dynamics, a Reinforcement Learning algorithm is developed that attains a stable Nash equilibrium for all types of games. Such an algorithm is lacking for the moment. This kind of dynamics opens an interesting perspective for introducing new Reinforcement Learning algorithms in multi-state games and Multi-Agent Systems.
Document URI:
ISBN: 3-540-20121-1
ISSN: 0302-9743
DOI: 10.1007/b13633
ISI #: 000187061900038
Category: A1
Type: Journal Contribution
Appears in Collections:Research publications

Show full item record

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.