Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/728
Title: Analyzing Multi-agent Reinforcement Learning Using Evolutionary Dynamics
Authors: 't Hoen, Pieter Jan
TUYLS, Karl 
Issue Date: 2004
Publisher: Springer
Source: MACHINE LEARNING: ECML 2004, PROCEEDINGS. p. 168-179
Series/Report: LECTURE NOTES IN COMPUTER SCIENCE
Series/Report no.: 3201
Abstract: In this paper, we show how the dynamics of Q-learning can be visualized and analyzed from a perspective of Evolutionary Dynamics (ED). More specifically, we show how ED can be used as a model for Q-learning in stochastic games. Analysis of the evolutionary stable strategies and attractors of the derived ED from the Reinforcement Learning (RL) application then predict the desired parameters for RL in Multi-Agent Systems (MASs) to achieve Nash equilibriums with high utility. Secondly, we show how the derived fine tuning of parameter settings from the ED can support application of the COllective INtelligence (COIN) framework. COIN is a proved engineering approach for learning of cooperative tasks in MASs. We show that the derived link between ED and RL predicts performance of the COIN framework and visualizes the incentives provided in COIN toward cooperative behavior.
Document URI: http://hdl.handle.net/1942/728
ISBN: 3-540-23105-6
ISSN: 0302-9743
DOI: 10.1007/978-3-540-30115-8_18
ISI #: 000223999500018
Category: A1
Type: Journal Contribution
Appears in Collections:Research publications

Show full item record

WEB OF SCIENCETM
Citations

4
checked on May 29, 2022

Page view(s)

60
checked on May 28, 2022

Google ScholarTM

Check

Altmetric


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