CSE 590A: Reinforcement Learning


Spring 2015
Wednesdays at 5:00
CSE 305 (unless otherwise noted)
Dan Weld, Chris Lin


Date Room Speaker / Presenter Topic
4/1 CSE 305 Organizational meeting
4/8 Gates Commons Chris Lin Reinforcement Learning Basics
4/15 CSE 305 Travis Mandel An empirical evaluation of Thompson sampling.
Efficient Reinforcement Learning via Posterior Sampling
4/22 CSE 305 Chris Lin Policy Gradient Methods for Reinforcement Learning with Function Approximation
Guided Policy Search
4/29 CSE 305 Angli Liu Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
5/6 CSE 305 Congle Zhang Human-level Control Through Deep Reinforcement Learning
5/13 CSE 305 Koosha Khalvati Bayes-Adaptive POMDPs. (For the original, older conference version see here.)
5/20 CSE 305 Travis Mandel Offline Policy Evaluation Across Representations with Applications to Educational Games
5/27 CSE 305 No Seminar This Week
6/3 CSE 305 Nancy Wang Closing the Learning-Planning Loop with Predictive State Representations