About Me

I am a Ph.D. candidate at Stanford University, advised by Emma Brunskill. Before 2017, I was a Ph.D. student at CMU advised by Emma Brunskill. I obtained my B.S. in Machine Intelligence from Peking University in 2016. As an undergraduate, I was interested in machine learning theory and optimization, and had the fortune of doing research under the supervision of Liwei Wang.


I am motivated by advancing reinforcement learning (RL) in real-world applications where sample cost and safety would be huge challenges. Thus I am interested in RL algorithms that collect and use sample more efficiently with provable guarantees, especially in off-line manner. The main problems I am interested in are also known as efficient exploration and off-policy (batch) RL. I am also attracted by other problems about learning from interactions, including contextual bandits problem, imitation learning, and causal inference. I am interested in applications of these methods in helping more people, for examples healthcare and education.


I am visiting Simons Institute for the theory of reinforcement learning program in this fall.




Workshop Papers

Invited Talks

Provably Good Batch Reinforcement Learning Without Great Exploration (Host: Prof Jiantao Jiao, UC Berkeley, 10/2020)

On the Variance of Conditional Importance Sampling for Off-Policy Evaluation (Causal Inference Seminar, Stanford, 10/2019)


CS234: Reinforcement Learning, Teaching Assistant, Winter 2019-2020.

CS229: Machine Learning, Teaching Assistant, Spring 2020-2021.

Professional Service

Journal Reviewing: JMLR, IEEE TPAMI, Biometrika, Machine Learning

Conference Reviewing: NeurIPS (2019 - ), ICLR (2019 - ), ICML(2020 - ), AISTATS (2020 - ), UAI(2020)