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 interactive learning, such as reinforcement learning, contextual bandits, and causal inference. Currently, I am working on two "opposite" directions: batch RL (a.k.a. off-policy/offline RL) -- how to learn from the exploratory data solely, and exploration in RL -- how to explore the environment efficiently. I am also interested in unsupervised/self-supervised learning and the theory of deep neural networks.

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

Interaction-Grounded Learning.
Tengyang Xie, John Langford, Paul Mineiro, Ida Momennejad
International Conference on Machine Learning (ICML) 2021.

Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency. [PDF, arXiv]
Masatoshi Uehara, Masaaki Imaizumi, Nan Jiang, Nathan Kallus, Wen Sun, Tengyang Xie

A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting. [PDF, arXiv]
Philip Amortila*, Nan Jiang*, Tengyang Xie*

Batch Value-function Approximation with Only Realizability. [PDF, arXiv]
Tengyang Xie, Nan Jiang
International Conference on Machine Learning (ICML) 2021.

Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison. [PDF, arXiv]
Tengyang Xie, Nan Jiang
Conference on Uncertainty in Artificial Intelligence (UAI) 2020.

Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling. [PDF, Poster, arXiv]
Tengyang Xie, Yifei Ma, Yu-Xiang Wang
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, Poster, arXiv]
Yu Bai, Tengyang Xie, Nan Jiang, Yu-Xiang Wang
Conference on Neural Information Processing Systems (NeurIPS) 2019.

A Block Coordinate Ascent Algorithm for Mean-Variance Optimization. [PDF, Poster, Link]
Tengyang Xie*, Bo Liu*, Yangyang Xu, Mohammad Ghavamzadeh, Yinlam Chow, Daoming Lyu, Daesub Yoon
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.)

Service

Conference Reviewer/Program Committee: NeurIPS (2020, 2019), ICML (2021, 2020, 2019), AISTATS (2020), AAAI (2020, 2019).
Journal Reviewer: Machine Learning Journal.
Program Committee for NeurIPS 2019 Optimization Foundations of Reinforcement Learning Workshop.
Program Committee for ICML 2020 Theoretical Foundations of Reinforcement Learning Workshop.
Program Committee for NeurIPS 2020 Offline Reinforcement Learning Workshop.