Not Logged In

Reinforcement Learning for 3 vs. 2 Keepaway

As a sequential decision problem, robotic soccer can benefit from research in reinforcement learning. We introduce the 3 vs. 2 keepaway domain, a subproblem of robotic soccer implemented in the RoboCup soccer server. We then explore reinforcement learning methods for policy evaluation and action selection in this distributed, real-time, partially observable, noisy domain. We present empirical results demonstrating that a learned policy can dramatically outperform hand-coded policies.

Citation

P. Stone, R. Sutton, S. Singh. "Reinforcement Learning for 3 vs. 2 Keepaway". RoboCup, January 2001.

Keywords: sequential, domain, soccer, machine learning
Category: In Workshop

BibTeX

@misc{Stone+al:RoboCup01,
  author = {Peter Stone and Richard S. Sutton and Satinder Singh},
  title = {Reinforcement Learning for 3 vs. 2 Keepaway},
  booktitle = {},
  year = 2001,
}

Last Updated: January 04, 2007
Submitted by Christian Smith

University of Alberta Logo AICML Logo