Improving the Learning Rate by Inducing a Transition Model

Date

2004

Authors

Bridle, Robert
McCreath, Eric

Journal Title

Journal ISSN

Volume Title

Publisher

Association for Computing Machinery Inc (ACM)

Abstract

In general, a reinforcement learning agent requires many trials in order to find a successful policy in a domain. In this paper we investigate inducing a transition model to reduce the number of trials required by an agent. We discuss an approach that incorporates transition model learning within a contemporary agent design.

Description

Keywords

Keywords: Reinforcement learning agents; Transition models; Approximation theory; Computational complexity; Dynamic programming; Feedback; Learning systems; Mathematical models; Regression analysis; Multi agent systems

Citation

Source

Proceedings of the Third International Joint Conference on Autonomous Agents & Multi Agent Systems (AAMAS 2004)

Type

Conference paper

Book Title

Entity type

Access Statement

License Rights

DOI

Restricted until