Temporal difference (TD) learning methods have become popular reinforcement learning techniques in recent years. TD methods, relying on function approximators to generalize learning to novel situations, have had some experimental successes and have been shown to exhibit some desirable properties in theory, but have often been found slow in practice. This paper presents methods for further generalizing emphacross tasks, thereby speeding up learning, via a novel form of emphbehavior transfer. We compare learning on a complex task with three function approximators, a CMAC, a neural network, and an RBF, and demonstrate that behavior transfer works well with all three. Using behavior transfer, agents are able to learn one task and then markedly reduce the time it takes to learn a more complex task. Our algorithms are fully implemented and tested in the RoboCup-soccer keepaway domain.

PDF, PS, HTML

In Proceedings of the Twentieth National Conference on Artificial Intelligence, July 2005.

@InProceedings{AAAI05-transfer, title={Value Functions for RL-Based Behavior Transfer: A Comparative Study}, author={Matthew E. Taylor and Peter Stone and Yaxin Liu}, booktitle={Proceedings of the Twentieth National Conference on Artificial Intelligence}, month={July}, url="http://nn.cs.utexas.edu/?AAAI05-transfer", year={2005} }