Keywords

neural nets, reinforcement learning systems, Q-learning systems, neural networks

Abstract

Reinforcement learning agents interacting in a common environment often fail to converge to optimal system behaviors even when the individual goals of the agents are fully compatible. Claus and Boutilier have demonstrated that the use of joint action learning helps to overcome these difficulties for Q-learning systems. This paper studies an application of joint action learning to systems of neural networks. Neural networks are a desirable candidate for such augmentations for two reasons: (1) they may be able to generalize more effectively than Q-learners, and (2) the network topology used may improve the scalability of joint action learning to systems with large numbers of agents. Preliminary results indicate that neural nets benefit from joint action learning in the same way that Q-learners do.

Original Publication Citation

Nancy Fulda and Dan Ventura, "Concurrently Learning Neural Nets: Encouraging Optimal Behavior in Cooperative Reinforcement Learning Systems", Proceedings of the IEEE International Workshop on Soft Computing Techniques in Instrumentation, Measurement, and Related Applications, pp. 2-5, May 23.

Document Type

Peer-Reviewed Article

Publication Date

2003-05-01

Permanent URL

http://hdl.lib.byu.edu/1877/2520

Publisher

IEEE

Language

English

College

Physical and Mathematical Sciences

Department

Computer Science

Share

COinS