Tengyang Xie

Hi! I'm a final-year Ph.D. candidate in Computer Science at University of Illinois at Urbana-Champaign (UIUC), where I am fortunate to work with Nan Jiang. Prior to UIUC, I received master degree in Computer Science from University of Massachusetts Amherst. Before that, I obtained bachelor's degree in Physics from University of Science and Technology of China (USTC). I have also spent time at Simons Institute, Amazon AI, Microsoft Research, and Google Research.

Research Interests: I work on Machine Learning. The primary goal of my research is to design provably efficient and practical algorithms relevant to modern machine learning paradigms, especially Reinforcement Learning and Representation Learning. My current interests include:
(1) Reinforcement learning from offline data, e.g., offline RL with general function approximation and arbitrary offline data, and best of both worlds from offline RL and imitation learning, provably and scalably (MSR blog).
(2) Reinforcement learning from (rich) human feedback, e.g., how to align AI through human interactions, and beyond.
(3) Theoretical foundations of machine learning, e.g., connecting the learability conditions between online and offline RL.
(4) Foundation models for decision making.
Recently, I am also working on their applications to networked systems and human-computer/AI interaction.

I am currently on the job market!

Publications

(Fun fact: My first/co-first authored papers had 100% acceptance rate at ICML(3)/NeurIPS(4)/ICLR(1)/UAI(1) during my PhD at UIUC, and 3/9 of them got oral or paper award.)

The Role of Coverage in Online Reinforcement Learning. [PDF, arXiv]
Tengyang Xie*, Dylan J. Foster*, Yu Bai, Nan Jiang, Sham M. Kakade
International Conference on Learning Representations (ICLR) 2023 (Notable-top-5% / Oral, acceptance rate: 1.8%)

ARMOR: A Model-based Framework for Improving Arbitrary Baseline Policies with Offline Data. [PDF, arXiv]
Tengyang Xie, Mohak Bhardwaj, Nan Jiang, Ching-An Cheng
Offline RL Workshop at NeurIPS 2022

Interaction-Grounded Learning with Action-Inclusive Feedback. [PDF, arXiv]
Tengyang Xie*, Akanksha Saran*, Dylan J. Foster, Lekan Molu, Ida Momennejad, Nan Jiang, Paul Mineiro, John Langford
Conference on Neural Information Processing Systems (NeurIPS) 2022
Complex Feedback in Online Learning Workshop at ICML 2022

Adversarially Trained Actor Critic for Offline Reinforcement Learning. [PDF, arXiv, code, MSR blog]
Ching-An Cheng*, Tengyang Xie*, Nan Jiang, Alekh Agarwal
International Conference on Machine Learning (ICML) 2022 (Outstanding Paper Runner-up Award)

Bellman-consistent Pessimism for Offline Reinforcement Learning. [PDF, arXiv, slides]
Tengyang Xie, Ching-An Cheng, Nan Jiang, Paul Mineiro, Alekh Agarwal
Conference on Neural Information Processing Systems (NeurIPS) 2021 (Oral, acceptance rate: 0.6%)

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning. [PDF, arXiv]
Tengyang Xie, Nan Jiang, Huan Wang, Caiming Xiong, Yu Bai
Conference on Neural Information Processing Systems (NeurIPS) 2021

Interaction-Grounded Learning. [PDF, arXiv, add'l supplement]
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
Submitted, 2021.

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, EWRL
Journal Reviewer: IEEE Transactions on Pattern Analysis and Machine Intelligence, Annals of Statistics, IEEE Transactions on Information Theory, Springer Machine Learning Journal.
Workshop Program Committee: Optimization Foundations of RL @ NeurIPS 2019, Theoretical Foundations of RL @ ICML 2020 & 2021, Offline RL @ NeurIPS 2020-2022, RL for Real Life @ ICML 2021 & NeurIPS 2022.