publications

* denotes equal contribution, † denotes alphabetical order.

2024

  1. NeurIPS 2024
    Provable Partially Observable Reinforcement Learning with Privileged Information
    Yang Cai†, Xiangyu Liu†, Argyris Oikonomou†, and Kaiqing Zhang†
    Advances in Neural Information Processing Systems, 2024
    A shorter version also presented at ICML 2024 ARLET workshop. Full version coming soon.
  2. Arxiv
    Do LLM Agents Have Regret? A Case Study in Online Learning and Games
    Chanwoo Park*, Xiangyu Liu*, Asuman Ozdaglar, and Kaiqing Zhang
    arXiv preprint arXiv:2403.16843, 2024
    arXiv
  3. Arxiv
    Is Poisoning a Real Threat to LLM Alignment? Maybe More So Than You Think
    Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang, and Furong Huang
    arXiv preprint arXiv:2406.12091, 2024
    arXiv
  4. ICLR 2024
    Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
    Xiangyu Liu, Souradip Chakraborty, Yanchao Sun, and Furong Huang
    In The Twelfth International Conference on Learning Representations, 2024
    A preliminary version is selected at NeurIPS 2022 Trustworthy and Socially Responsible Machine Learning (TSRML) workshop as an outstanding paper
    arXiv Code
  5. ICLR 2024 (spotlight)
    Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
    Xiangyu Liu*, Chenghao Deng*, Yanchao Sun, Yongyuan Liang, and Furong Huang
    In The Twelfth International Conference on Learning Representations, 2024
    arXiv Code Website
  6. ICLR 2024
    Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
    Yongyuan Liang, Yanchao Sun, Ruijie Zheng, Xiangyu Liu, Benjamin Eysenbach, Tuomas Sandholm, Furong Huang, and Stephen McAleer
    In The Twelfth International Conference on Learning Representations, 2024
    arXiv

2023

  1. ICML 2023
    Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing
    Xiangyu Liu, and Kaiqing Zhang
    In International Conference on Machine Learning, 2023
    Extended version under review at SIAM Journal on Control and Optimization (SICON)
    arXiv

2021

  1. NeurIPS 2021
    Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games
    Xiangyu Liu, Hangtian Jia, Ying Wen, Yujing Hu, Yingfeng Chen, Changjie Fan, Zhipeng Hu, and Yaodong Yang
    Advances in Neural Information Processing Systems, 2021
    Code Website