IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Reinforcement Learning with Reward Shaping and Mixed Resolution Function Approximation

Reinforcement Learning with Reward Shaping and Mixed Resolution Function Approximation
View Sample PDF
Author(s): Marek Grzes (University of York, UK) and Daniel Kudenko (University of York, UK)
Copyright: 2009
Volume: 1
Issue: 2
Pages: 19
Source title: International Journal of Agent Technologies and Systems (IJATS)
DOI: 10.4018/jats.2009040103

Purchase

View Reinforcement Learning with Reward Shaping and Mixed Resolution Function Approximation on the publisher's website for pricing and purchasing information.

Abstract

A crucial trade-off is involved in the design process when function approximation is used in reinforcement learning. Ideally the chosen representation should allow representing as close as possible an approximation of the value function. However, the more expressive the representation the more training data is needed because the space of candidate hypotheses is bigger. A less expressive representation has a smaller hypotheses space and a good candidate can be found faster. The core idea of this paper is the use of a mixed resolution function approximation, that is, the use of a less expressive function approximation to provide useful guidance during learning, and the use of a more expressive function approximation to obtain a final result of high quality. A major question is how to combine the two representations. Two approaches are proposed and evaluated empirically.

Related Content

Pinki Sharma, Jyotsna Sengupta, P. K. Suri. © 2019. 17 pages.
Sukhdev Singh, Chander Kant. © 2019. 7 pages.
Sahil Chhabra, Neeraj Kumar Jain, Vipin Tomar. © 2019. 9 pages.
Alankrita Aggarwal, Deepak Chatha. © 2019. 10 pages.
Smiley Gupta, Jagtar Singh. © 2019. 10 pages.
Meenakshi Sharma, Sonia Thind. © 2019. 10 pages.
Jimmy Singla. © 2019. 9 pages.
Body Bottom