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 machine 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

Bellman-consistent Pessimism for Offline Reinforcement Learning. [PDF, arXiv]
Tengyang Xie, Ching-An Cheng, Nan Jiang, Paul Mineiro, Alekh Agarwal

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning. [PDF, arXiv]
Tengyang Xie, Nan Jiang, Huan Wang, Caiming Xiong, Yu Bai

Interaction-Grounded Learning. [PDF, arXiv]
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, ICML, AISTATS, AAAI.
Journal Reviewer: Machine Learning Journal.
Workshop Program Committee: Optimization Foundations of RL @ NeurIPS 2019, Theoretical Foundations of RL @ ICML 2020 & 2021, Offline RL @ NeurIPS 2020, RL for Real Life @ ICML 2021.