Successor Features for Transfer in Reinforcement Learning

Andre Barreto, Will Dabney, Remi Munos, Jonathan J. Hunt, Tom Schaul, Hado P. van Hasselt, David Silver

Neural Information Processing Systems 

We propose a transfer framework for the scenario where the reward function changes between tasks but the environment's dynamics remain the same.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found