Accession Number : AD1024624

Title :   Autonomous Inter-Task Transfer in Reinforcement Learning Domains

Descriptive Note : Technical Report

Corporate Author : University of Texas at Austin Austin United States

Personal Author(s) : Taylor,Matthew E

Full Text :

Report Date : 01 Aug 2008

Pagination or Media Count : 319

Abstract : Reinforcement learning (RL) methods have become popular in recent years because of their ability to solve complex tasks with minimal feedback. While these methods have had experimental successes and have been shown to exhibit some desirable properties in theory, the basic learning algorithms have often been found slow in practice. Therefore, much of the current RL research focuses on speeding up learning by taking advantage of domain knowledge, or by better utilizing agents experience. The ambitious goal of transfer learning, when applied to RL tasks, is to accelerate learning on some target task after training on a different, but related, source task. This dissertation demonstrates that transfer learning methods can successfully improve learning in RL tasks via experience from previously learned tasks.

Descriptors :   artificial intelligence , artificial neural networks , artificial intelligence software , computer programs , transfer functions , machine learning , theses

Subject Categories : Computer Programming and Software

Distribution Statement : APPROVED FOR PUBLIC RELEASE