The WhiRL Reading Group takes places weekly on Tuesdays, 15:00 at Tony Hoare room, Robert Hooke building.
The next topic is:
>> Deep Variational Reinforcement Learning for POMDPs << (Tuesday, June 19th)
Abstract: 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 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. (preprint see here)
It is open for all. To add your email to the mailing list, please fill out the form below:
Past reading groups:
>> Simple random search provides a competitive approach to reinforcement learning << (Tuesday, April 10)
>> Latent Space Policies for Hierarchical Reinforcement Learning << (Tuesday, April 17th)