Sciweavers

Share
AI
2002
Springer

Multiagent learning using a variable learning rate

9 years 3 months ago
Multiagent learning using a variable learning rate
Learning to act in a multiagent environment is a difficult problem since the normal definition of an optimal policy no longer applies. The optimal policy at any moment depends on the policies of the other agents. This creates a situation of learning a moving target. Previous learning algorithms have one of two shortcomings depending on their approach. They either converge to a policy that may not be optimal against the specific opponents' policies, or they may not converge at all. In this article we examine this learning problem in the framework of stochastic games. We look at a number of previous learning algorithms showing how they fail at one of the above criteria. We then contribute a new reinforcement learning technique using a variable learning rate to overcome these shortcomings. Specifically, we introduce the WoLF principle, "Win or Learn Fast," for varying the learning rate. We examine this technique theoretically, proving convergence in self-play on a restrict...
Michael H. Bowling, Manuela M. Veloso
Added 16 Dec 2010
Updated 16 Dec 2010
Type Journal
Year 2002
Where AI
Authors Michael H. Bowling, Manuela M. Veloso
Comments (0)
books