Learning RoboCup-Keepaway with Kernels

Details Learning RoboCup-Keepaway with Kernels Learning RoboCup-Keepaway with Kernels

2012-01-31

arxiv.org/abs/1201.6626v1

JMLR Workshop and Conference Proceedings (1st Gaussian Processes in Practice Workshop, 2006)

Computer Science

Artificial Intelligence

Scientific paper

We apply kernel-based methods to solve the difficult reinforcement learning problem of 3vs2 keepaway in RoboCup simulated soccer. Key challenges in keepaway are the high-dimensionality of the state space (rendering conventional discretization-based function approximation like tilecoding infeasible), the stochasticity due to noise and multiple learning agents needing to cooperate (meaning that the exact dynamics of the environment are unknown) and real-time learning (meaning that an efficient online implementation is required). We employ the general framework of approximate policy iteration with least-squares-based policy evaluation. As underlying function approximator we consider the family of regularization networks with subset of regressors approximation. The core of our proposed solution is an efficient recursive implementation with automatic supervised selection of relevant basis functions. Simulation results indicate that the behavior learned through our approach clearly outperforms the best results obtained earlier with tilecoding by Stone et al. (2005).

Affiliated with

Also associated with

No associations

Rating

Learning RoboCup-Keepaway with Kernels does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning RoboCup-Keepaway with Kernels, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning RoboCup-Keepaway with Kernels will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-57537