Explorations of the Practical Issues of Learning Prediction-Control Tasks Using Temporal Difference Learning Methods

dc.creator	Isbell, Charles L.
dc.date	2004-10-20T20:23:50Z
dc.date	2004-10-20T20:23:50Z
dc.date	1992-12-01
dc.date.accessioned	2013-10-09T02:48:06Z
dc.date.available	2013-10-09T02:48:06Z
dc.date.issued	2013-10-09
dc.identifier	AITR-1424
dc.identifier	http://hdl.handle.net/1721.1/7050
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	There has been recent interest in using temporal difference learning methods to attack problems of prediction and control. While these algorithms have been brought to bear on many problems, they remain poorly understood. It is the purpose of this thesis to further explore these algorithms, presenting a framework for viewing them and raising a number of practical issues and exploring those issues in the context of several case studies. This includes applying the TD(lambda) algorithm to: 1) learning to play tic-tac-toe from the outcome of self-play and of play against a perfectly-playing opponent and 2) learning simple one-dimensional segmentation tasks.
dc.format	223511 bytes
dc.format	456055 bytes
dc.format	application/octet-stream
dc.format	application/pdf
dc.language	en_US
dc.relation	AITR-1424
dc.title	Explorations of the Practical Issues of Learning Prediction-Control Tasks Using Temporal Difference Learning Methods

Files in this item

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