Using the XCS classifier system for multi-objective reinforcement learning problems

Studley, M. and Bull, L. (2007) Using the XCS classifier system for multi-objective reinforcement learning problems. Artificial Life, 13 (1). pp. 69-86. ISSN 1064-5462

[img]
Preview
PDF - Published Version
258kB

Publisher's URL: http://dx.doi.org/10.1162/artl.2007.13.1.69


Item Type:Article
Additional Information:XCS is a Learning Classifier System (LCS), in which evolutionary search techniques and reinforcement learning are used to discover general rule-sets which optimally solve a given problem. This paper presents the first published work applying a LCS to problems with more than one goal that must be solved optimally. Examples might be robots which must learn to recharge their batteries, learn to perform useful work, and learn the optimal balance between the two. It is shown that XCS is capable of solving such problems but that its ability to do so is related to its action selection policy. This extends previously published XCS theory. Conclusions from experimental data suggest some design considerations for XCS use on physical robots where resources may be limited. The authors built upon this work to demonstrate the first implementation of a multiple-goal XCS-based system on a real robot.
Uncontrolled Keywords:action selection, autonomous agents, genetic algorithm, population size
Faculty/Department:Faculty of Environment and Technology
ID Code:5914
Deposited By: R. Upload account
Deposited On:22 Jan 2010 15:10
Last Modified:24 May 2014 04:52

Request a change to this item

Total Document Downloads in Past 12 Months

Document Downloads

Total Document Downloads

More statistics for this item...
Copyright 2013 © UWE better together