VIREL: A Variational Inference Framework for Reinforcement Learning

Matthew Fellows, Anuj Mahajan, Tim G. J. Rudner, Shimon Whiteson

Neural Information Processing Systems 

Applying probabilistic models to reinforcement learning (RL) enables the uses of powerful optimisation tools such as variational inference in RL.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found