A Comparative Analysis of Reinforcement Learning Methods

dc.creator	Mataric, Maja
dc.date	2004-10-04T14:25:16Z
dc.date	2004-10-04T14:25:16Z
dc.date	1991-10-01
dc.date.accessioned	2013-10-09T02:42:10Z
dc.date.available	2013-10-09T02:42:10Z
dc.date.issued	2013-10-09
dc.identifier	AIM-1322
dc.identifier	http://hdl.handle.net/1721.1/5978
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	This paper analyzes the suitability of reinforcement learning (RL) for both programming and adapting situated agents. We discuss two RL algorithms: Q-learning and the Bucket Brigade. We introduce a special case of the Bucket Brigade, and analyze and compare its performance to Q in a number of experiments. Next we discuss the key problems of RL: time and space complexity, input generalization, sensitivity to parameter values, and selection of the reinforcement function. We address the tradeoffs between the built-in and learned knowledge and the number of training examples required by a learning algorithm. Finally, we suggest directions for future research.
dc.format	13 p.
dc.format	1444645 bytes
dc.format	1130480 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-1322
dc.subject	reinforcement
dc.subject	learning
dc.subject	situated agents
dc.subject	inputsgeneralization
dc.subject	complexity
dc.subject	built-in knowledge
dc.title	A Comparative Analysis of Reinforcement Learning Methods

Files in this item

Files	Size	Format	View
There are no files associated with this item.