Tian Xu

alt text 

Assistant Researcher,
School of Artificial Intelligence,
Nanjing University
[Google Scholar] [CV]

Email: xut@lamda.nju.edu.cn

About me

Welcome to my homepage! Currently, I am an assistant researcher (Yuxiu Young Scholar) in the School of Artificial Intelligence at Nanjing University, and I am also a member of LAMDA Group and LAMDA-RL Group.

  • [Sep 2019 - Jun 2025]: I obtained my Ph.D. degree in Computer Science from Nanjing University (School of Artificial Intelligence), where I was fortunate to be advised by Prof. Yang Yu.

  • [Jun 2021 - Sep 2021]: I visited The Chinese University of Hong Kong, Shenzhen (CUHKSZ) from June to September in 2021, where I was fortunate to be supervised by Prof. Zhi-Quan (Tom) Luo.

  • [Sep 2015 - Jun 2019]: I obtained my B.Sc. degree in Mathematics and Applied Mathematics from Northwestern Polytechnical University.

My research interests lie in the theoretical foundation and algorithmic design in reinforcement learning. Curretly, I am mainly working on imitation learning, reinforcement learning and their applications in large language models.

Selected Work

*: indicating equal contribution.

  • Imitation Learning from Imperfection: Theoretical Justifications and Algorithms.
    Ziniu Li*, Tian Xu*, Zeyu Qin, Yang Yu, Zhi-Quan Luo
    In Advances in Neural Information Process System 36 (NeurIPS, spotlight), 2023.
    (This work proposes a data-selection-based method ISW-BC to address the distribution shift issue in IL with imperfect demonstrations.
    We prove that ISW-BC is robust to OOD samples and enjoys a small imitation gap bound.)

  • Provably Efficient Adversarial Imitation Learning with Unknown Transitions
    Tian Xu*, Ziniu Li*, Yang Yu, Zhi-Quan Luo
    In Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI, oral presentation, acceptance rate < 3% ), 2023
    (This work proposes an “exploration-estimation-optimizatoin” error decomposition analysis for AIL in the unknown transition setting.
    Based on this analysis, we derive a new method MB-TAIL, which achieves the optimal expert sample complexity and better interaction complexity.)

  • Rethinking ValueDice: Does It Really Improve Performance?
    Ziniu Li*, Tian Xu*, Yang Yu, Zhi-Quan Luo
    In Proceedings of the 10th International Conference on Learning Representations (ICLR) (Blog Track), 2022
    (This work demonstrates the first reduction of offline adversarial imitation learning (AIL) to BC, implying that AIL does not outperform BC in the offline setting.)

  • Error Bounds of Imitating Policies and Environments
    Tian Xu*, Ziniu Li* , Yang Yu
    In Advances in Neural Information Processing Systems 33 (NeurIPS), 2020
    (This work presents a general analysis framework for imitation learning algorithms, upon which we first prove that
    GAIL-type methods can overcome the compounding errors issue of BC in both imitating policies and environments.)

Service

Reviewer

NeurIPS (2022-), ICML (2022-), ICLR (2024-), AISTATS (2024-), UAI (2021-), RLC (2024-), EWRL (2022-).

Award

  • [2020-10] National Scholarship for Graduates.

  • [2020-8] Second winner on KDD CUP 2020 Reinforcement Learning Competition Track.

  • [2016-9, 2017-9] National Scholarship for Undergraduates.