Tengyang Xie

Hi! I'm a Ph.D. student in Computer Science at University of Illinois at Urbana-Champaign (UIUC), where I am fortunate to work with Nan Jiang. My research mainly focuses on reinforcement learning (RL). Currently, I am working on two "opposite" directions: batch RL (i.e. off-policy RL) -- how to learn from the exploratory data solely, and exploration in RL -- how to explore the environment efficiently. I am also interested in the intersection between theory of deep neural networks and reinforcement learning.

I am delighted to complement my research with industrial experiences. I spent a wonderful summer working as a research intern at Amazon AI Palo Alto in 2018, with Yu-Xiang Wang and Yifei Ma.

Prior to UIUC, I was a Ph.D. student in Computer Science at University of Massachusetts Amherst, where I was introduced to RL and working with Phil Thomas. Before that, I obtained bachelor's degree in Physics from University of Science and Technology of China (USTC).

Publications

Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling. [PDF, arXiv]
Tengyang Xie, Yifei Ma, Yu-Xiang Wang
In Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019).
Spotlight presentation at the NeurIPS 2018 Workshop on Causal Learning.

Provably Efficient Q-Learning with Low Switching Cost. [PDF, arXiv]
Yu Bai, Tengyang Xie, Nan Jiang, Yu-Xiang Wang
In Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019).

A Block Coordinate Ascent Algorithm for Mean-Variance Optimization. [PDF, Poster]
Tengyang Xie*, Bo Liu*, Yangyang Xu, Mohammad Ghavamzadeh, Yinlam Chow, Daoming Lyu, Daesub Yoon
In Thirty-second Conference on Neural Information Processing Systems (NeurIPS 2018).

Privacy Preserving Off-policy Evaluation. [PDF, arXiv]
Tengyang Xie, Philip S. Thomas, Gerome Miklau

(* indicates equal contribution or alphabetic ordering.)

Teaching

TA.> CS187. Programming with Data Structures. UMass Amherst. Spring 2019
TA.> CS590M. Introduction to Simulation. UMass Amherst. Spring 2018
TA.> CS119. Introduction to Programming with Python. UMass Amherst. Fall 2017

Service

Reviewer/Program Committee: NeurIPS 2019, ICML 2020 2019, AISTATS 2020, AAAI 2020 2019.
Program Committee for NeurIPS 2019 Optimization Foundations of Reinforcement Learning Workshop.