Recent work in transfer learning has succeeded in Reinforcement learning agents typically require a significant amount of data before performing well on complex tasks. Transfer learning methods have made progress reducing sample complexity, but they have primarily been applied to model-free learning methods, not more data-efficient model-based learning methods. This paper introduces TIMBREL, a novel method capable of transferring information effectively into a model-based reinforcement learning algorithm. We demonstrate that TIMBREL can significantly improve the sample efficiency and asymptotic performance of a model-based algorithm when learning in a continuous state space. Additionally, we conduct experiments to test the limits of TIMBREL's effectiveness.

PDF, PS, HTML

In Machine Learning and Knowledge Discovery in Databases, Vol. 5212, pp. 488-505, September 2008.

@inproceedings{ECML08-taylor, title={Transferring Instances for Model-Based Reinforcement Learning}, author={Matthew E. Taylor and Nicholas K. Jong and Peter Stone}, booktitle={Machine Learning and Knowledge Discovery in Databases}, volume={5212}, month={September}, series={Lecture Notes in Artificial Intelligence}, pages={488-505}, url="http://www.cs.utexas.edu/users/ai-lab?ECML08-taylor", year={2008} }