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

Title: en_US Explorations of the Practical Issues of Learning Prediction-Control Tasks Using Temporal Difference Learning Methods
Creator: en_US Isbell, Charles L.
Date: 2004-10-20T20:23:50Z
Date Available: 2004-10-20T20:23:50Z
Date Issued: en_US 1992-12-01
Identifier: en_US AITR-1424
uri: http://hdl.handle.net/1721.1/7050
Abstract: en_US 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.
Extent: 223511 bytes; 456055 bytes
Format: application/octet-stream; application/pdf
Language: en_US
Relation: en_US AITR-1424