Ziniu Li

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 23

Top Topics

Imitation Learning

Top Venues

IEEE Trans. Pattern Anal. Mach. Intell.

Publications

Jiancong Xiao, Ziniu Li, Xingyu Xie, Emily J. Getzen, Cong Fang, Qi Long, Weijie J. Su
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization. CoRR (2024)
Yushun Zhang, Congliang Chen, Tian Ding, Ziniu Li, Ruoyu Sun, Zhi-Quan Luo
Why Transformers Need Adam: A Hessian Perspective. CoRR (2024)
Yushun Zhang, Congliang Chen, Ziniu Li, Tian Ding, Chenwei Wu, Yinyu Ye, Zhi-Quan Luo, Ruoyu Sun
Adam-mini: Use Fewer Learning Rates To Gain More. CoRR (2024)
Chengxing Jia, Pengyuan Wang, Ziniu Li, Yi-Chen Li, Zhilong Zhang, Nan Tang, Yang Yu
BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation. CoRR (2024)
Ziniu Li, Tian Xu, Yang Yu
When is RL better than DPO in RLHF? A Representation and Optimization Perspective. Tiny Papers @ ICLR (2024)
Ziniu Li, Tian Xu, Yang Yu
Policy Optimization in RLHF: The Impact of Out-of-preference Data. CoRR (2023)
Ziniu Li, Tian Xu, Zeyu Qin, Yang Yu, Zhi-Quan Luo
Imitation Learning from Imperfection: Theoretical Justifications and Algorithms. NeurIPS (2023)
Tian Xu, Ziniu Li, Yang Yu, Zhi-Quan Luo
Provably Efficient Adversarial Imitation Learning with Unknown Transitions. UAI (2023)
Tian Xu, Ziniu Li, Yang Yu, Zhi-Quan Luo
Provably Efficient Adversarial Imitation Learning with Unknown Transitions. CoRR (2023)
Ziniu Li, Tian Xu, Yang Yu, Zhi-Quan Luo
Theoretical Analysis of Offline Imitation With Supplementary Dataset. CoRR (2023)
Ziniu Li, Tian Xu, Yushun Zhang, Yang Yu, Ruoyu Sun, Zhi-Quan Luo
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models. CoRR (2023)
Ziniu Li, Ke Xu, Liu Liu, Lanqing Li, Deheng Ye, Peilin Zhao
Deploying Offline Reinforcement Learning with Human Feedback. CoRR (2023)
Tian Xu, Ziniu Li, Yang Yu
Error Bounds of Imitating Policies and Environments for Reinforcement Learning. IEEE Trans. Pattern Anal. Mach. Intell. 44 (10) (2022)
Tian Xu, Ziniu Li, Yang Yu, Zhi-Quan Luo
Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis. CoRR (2022)
Ziniu Li, Yingru Li, Yushun Zhang, Tong Zhang, Zhi-Quan Luo
HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning. ICLR (2022)
Ziniu Li, Tian Xu, Yang Yu
A Note on Target Q-learning For Solving Finite MDPs with A Generative Oracle. CoRR (2022)
Ziniu Li, Tian Xu, Yang Yu, Zhi-Quan Luo
Rethinking ValueDice: Does It Really Improve Performance? CoRR (2022)
Tian Xu, Ziniu Li, Yang Yu
Nearly Minimax Optimal Adversarial Imitation Learning with Known and Unknown Transitions. CoRR (2021)
Tian Xu, Ziniu Li, Yang Yu
Error Bounds of Imitating Policies and Environments. NeurIPS (2020)
Tian Xu, Ziniu Li, Yang Yu
Error Bounds of Imitating Policies and Environments. CoRR (2020)
Ziniu Li, Xiong-Hui Chen
Efficient Exploration by Novelty-Pursuit. DAI (2020)
Xinjian Huang, Ziniu Li, Zhiyuan Liu, Bin Xiang, Yingsan Geng, Jianhua Wang
Solving the Inverse Design Problem of Electrical Fuse With Machine Learning. IEEE Access 8 (2020)
Tian Xu, Ziniu Li, Yang Yu
On Value Discrepancy of Imitation Learning. CoRR (2019)