R. Maclin, J. Shavlik, L. Torrey & T. Walker (2005).
Knowledge Based Support Vector Regression for Reinforcement Learning. IJCAI'05 Workshop on Reasoning, Representation, and Learning in Computer Games, Edinburgh, Scotland.
This publication is contained in the following 2 PDF files
File 1, File 2.
Reinforcement learning (RL) methods have difficulty scaling to large, complex problems. One approach that has proven effective for scaling RL is to make use of advice provided by a human. We extend a recent advice-giving technique, called Knowledge-Based Kernel Regression (KBKR), to RL and evaluate our approach on the KeepAway subtask of the RoboCup soccer simulator. We present empirical results that show our approach can make effective use of advice. Our work not only demonstrates the potential of advice-giving techniques such as KBKR for RL, but also offers insight into some of the design decisions involved in employing support-vector regression in RL.
Computer Sciences Department
College of Letters and Science
University of Wisconsin - Madison
INFORMATION ~ PEOPLE ~ GRADS ~ UNDERGRADS ~ RESEARCH ~ RESOURCES
5355a Computer Sciences and Statistics ~ 1210 West Dayton Street, Madison, WI 53706
firstname.lastname@example.org ~ voice: 608-262-1204 ~ fax: 608-262-9777