Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/731
Title: | On a Dynamical Analysis of Reinforcement Learning in Games: Emergence of Occam's Razor | Authors: | TUYLS, Karl Verbeeck, Katja Maes, Sam |
Issue Date: | 2003 | Publisher: | Springer | Source: | LECTURE NOTES IN ARTIFICIAL INTELLIGENCE, 2691. p. 335-344 | Abstract: | Modeling learning agents in the context of Multi-agent Systems requires an adequate understanding of their dynamic behaviour. Usually, these agents are modeled similar to the different players in a standard game theoretical model. Unfortunately traditional Game Theory is static and limited in its usefelness. Evolutionary Game Theory improves on this by providing a dynamics which describes how strategies evolve over time. In this paper, we discuss three learning models whose dynamics are related to the Replicator Dynamics(RD). We show how a classical Reinforcement Learning(RL) technique, i.e. Q-learning relates to the RD. This allows to better understand the learning process and it allows to determine how complex a RL model should be. More precisely, Occam's Razor applies in the framework of games, i.e. the simplest model (Cross) suffices for learning equilibria. An experimental verification in all three models is presented. | Document URI: | http://hdl.handle.net/1942/731 | Link to publication/dataset: | http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=2691&spage=335 | ISSN: | 0302-9743 | ISI #: | 000184854600032 | Category: | A1 | Type: | Journal Contribution |
Appears in Collections: | Research publications |
Show full item record
WEB OF SCIENCETM
Citations
1
checked on Sep 6, 2024
Page view(s)
90
checked on Nov 7, 2023
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.