Knowledge transfer via advice taking

Authors:
Lisa Torrey;Trevor Walker;Jude Shavlik;Richard Maclin
Affiliations:
University of Wisconsin, Madison, Madison, WI;University of Wisconsin, Madison, Madison, WI;University of Wisconsin, Madison, Madison, WI;University of Minnesota, Duluth, Duluth, MN
Venue:
Proceedings of the 3rd international conference on Knowledge capture
Year:
2005

Citing 3
Cited 1

Scaling Reinforcement Learning toward RoboCup Soccer

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Using advice to transfer knowledge acquired in one reinforcement learning task to another

ECML'05 Proceedings of the 16th European conference on Machine Learning

Experiments with Adaptive Transfer Rate in Reinforcement Learning

Knowledge Acquisition: Approaches, Algorithms and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a framework for knowledge transfer from one reinforcement learning task to a related task through advice-taking mechanisms. We discuss the importance of transfer in complex domains such as RoboCup soccer, and show how to use automatically generated advice to perform transfer.