The RL seminar covers various methods in reinforcement learning as well as its combination with deep learning (a.k.a Deep RL), from theory, to algorithms, to applications.

The seminar meets Mondays, 9:00-11:00 am (UTC+8), in 603 Administration Building.

Date	Speaker and Title
Jan 21	Jim Dai (iDDA, CUHK-Shenzhen) Introduction to reinforcement learning
Jan 28	Mark Gluzman (iDDA, CUHK-Shenzhen) Multi-step learning and Value-based approximation methods
Feb 04
Feb 11	Yingru Li (Tencent Joint Lab, CUHK-Shenzhen) Policy gradient methods
Feb 18	Lu Wang (East China Normal University & Tencent AI Lab) Option Discovery Algorithms
Feb 25	Huizhuo Yuan (Peking University & Tencent AI Lab) Scalable distributed RL (I)
Mar 04	Yige Hong (CUHK-Shenzhen) Trust Region and Proximal Policy Optimization
Mar 11	Hao Liang (CUHK-Shenzhen) Distributional RL
Mar 18	Mark Gluzman (iDDA, CUHK-Shenzhen) Increasing the Action Gap
Mar 25	Huizhuo Yuan (Peking University & Tencent AI Lab) Scalable distributed RL (II)
Apr 01
Apr 08	Siliang Zeng (CUHK-Shenzhen) Multi-Agent Reinforcement Learning for Adaptive Routing
Apr 15	Chang Cao (iDDA, CUHK-Shenzhen) Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning
Apr 22	Yingru Li (Tencent Joint Lab, CUHK-Shenzhen) Learning in Zero-Sum Games
Apr 29
May 06	Hao Liang (CUHK-Shenzhen) Information Theoretic Analysis of Thompson Sampling