Hi! I am Zichuan Lin, a fourth-year Ph.D. student in the Department of Computer Science and Technology, Tsinghua University, advised by Prof. Guangwen Yang.
I was a research intern at Microsoft Research Asia from Sep, 2016 to Mar, 2018 (advised by Lintao Zhang) and from May, 2018 to Jun, 2019 (advised by Tao Qin and Li Zhao). I will be joining SAIL at Stanford University as a visiting student researcher this Summer, advised by Prof. Tengyu Ma.
My research interests include deep reinforcement learning, imitation learning and meta learning. My goal is to develop sample-efficient reinforcement learning algorithms. Specifically, my research projects mainly involve episodic control, representation learning, distributional RL and multi-task RL.
(* represents equal contribution)
Episodic Reinforcement Learning with Associative Memory
Guangxiang Zhu*, Zichuan Lin*, Guangwen Yang, and Chongjie Zhang
Object-Oriented Dynamics Learning through Multi-Level Abstraction
Guangxiang Zhu*, Jianhao Wang*, Zhizhou Ren*, Zichuan Lin and Chongjie Zhang
Distributional Reward Decomposition for Reinforcement Learning
Zichuan Lin, Li Zhao, Derek Yang, Tao Qin, Guangwen Yang, and Tie-yan Liu
Fully Parameterized Quantile Function for Distributional Reinforcement Learning
Derek Yang, Li Zhao, Zichuan Lin, Jiang Bian, Tao Qin, and Tie-yan Liu
Unified Policy Optimization for Robust Reinforcement Learning
Zichuan Lin, Li Zhao, Jiang Bian, Tao Qin, and Guangwen Yang
ACML 2019 (Oral)
Unified Policy Optimization for Reinforcement Learning [slides]
Nagoya, Japan, 2019
Towards Sample-efficient, Interpretable and Robust Reinforcement Learning [slides]
Wuxi, China, 2019
Episodic Memory Deep Q-Networks [slides]
Stockholm, Sweden, 2018
Reinforcement Learning: Episodic Memory and Learning to Run [slides]
MSRA, Beijing, 2017