Poster
Deep Variational Reinforcement Learning for POMDPs
Maximilian Igl · Luisa Zintgraf · Tuan Anh Le · Frank Wood · Shimon Whiteson

Thu Jul 12th 06:15 -- 09:00 PM @ Hall B #199

Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinforcement learning methods that can tackle such problems given only a stream of rewards and incomplete and noisy observations. In this paper, we propose deep variational reinforcement learning (DVRL), which introduces an inductive bias that allows an agent to learn a generative model of the environment and perform inference in that model to effectively aggregate the available information. We develop an n-step approximation to the evidence lower bound (ELBO), allowing the model to be trained jointly with the policy. This ensures that the latent state representation is suitable for the control task. In experiments on Mountain Hike and flickering Atari we show that our method outperforms previous approaches relying on recurrent neural networks to encode the past.

Author Information

Maximilian Igl (University of Oxford)
Luisa Zintgraf (University of Oxford)
Tuan Anh Le (University of Oxford)
Frank Wood (University of British Columbia)
Shimon Whiteson (University of Oxford)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors