L. Torrey, T. Walker, J. Shavlik & R. Maclin (2005).
Using Advice to Transfer Knowledge Acquired in One Reinforcement Learning Task to Another. Proceedings of the Sixteenth European Conference on Machine Learning (ECML'05), pp. 412-424, Porto, Portugal.
This publication is available in PDF.
The slides for this publication are available in Microsoft PowerPoint.
We present a method for transferring knowledge learned in one task to a related task. Our problem solvers employ reinforcement learning to acquire a model for one task. We then transform that learned model into advice for a new task. A human teacher provides a mapping from the old task to the new task to guide this knowledge transfer. Advice is incorporated into our problem solver using a knowledge-based support vector regression method that we previously developed. This advice-taking approach allows the problem solver to refine or even discard the transferred knowledge based on its subsequent experiences. We empirically demonstrate the effectiveness of our approach with two games from the RoboCup soccer simulator: KeepAway and BreakAway. Our results demonstrate that a problem solver learning to play BreakAway using advice extracted from KeepAway outperforms a problem solver learning without the benefit of such advice.
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
email@example.com ~ voice: 608-262-1204 ~ fax: 608-262-9777