High-dimensional Statistics Reinforcement Learning

The seminar meets Thursday, 2:00-5:00 pm (UTC+8), in 603 Administration Building. We also provide online zoom meeting room for the convenience of discussion and replay.

Date	Speaker and Title
Jun 18	Yingru Li (CUHK-SZ) Basic tail and concentration bounds
Jun 24	Yingru Li (CUHK-SZ) Basic tail and concentration bounds
Jul 02	Hao Liang (CUHK-SZ) Minimax Lower Bounds
Jul 09	Ziniu Li (CUHK-SZ) Variance-reduced Q-Learning is minimax optimal
Jul 16	Qingyan Meng (CUHK-SZ) Uniform Law of Large Number
Jul 25	Yingru Li (CUHK-SZ) Lower bounds for Bandits and RL
Jul 30	Yingru Li (CUHK-SZ) Minimax regret upper bounds of UCBVI for RL
Aug 06	Jiancong Xiao (CUHK-SZ) Metric Entropy
Aug 12	Prof. Baoxiang Wang and Jie Wang (CUHK-SZ) (1) The Gambler's problem and beyond and (2) Off-Policy Evaluation - A Distributionally Robust Approach
Aug 20	Lizhang Miao (CUHK-SZ) Reinforcement Learning with Linear Function Approximation