Haoxin Lin

lhx.jpg

Ph.D. Student, LAMDA-RL Group
School of Artificial Intelligence
National Key Laboratory for Novel Software Technology
Nanjing University
Supervisor: Prof. Yang Yu
Email: linhx@lamda.nju.edu.cn

[ Google Scholar ] [ DBLP ] [ Research Gate ] [ GitHub ] [ Zhihu ]

Biography

Currently, I am a first-year Ph.D. student of School of Artificial Intelligence in Nanjing University under the supervision of Prof. Yang Yu and also a member of LAMDA Group, which is led by Prof. Zhi-Hua Zhou.

Before my doctoral phase, I received my B.Sc. degree in Telecommunication Engineering in 2021 from Sun Yat-sen University . In September 2021, I was admitted to study for a M.Sc. degree in Nanjing University under the supervision of Prof. Yang Yu without entrance examination. From September 2024, I started studying for a Ph.D. degree under the supervision of Prof. Yang Yu.

Research Interests

I am interested in handling challenges of Reinforcement Learning (RL) in real-world applications. In particular, I focus my research topics on model-based RL and offline RL. I am also working to develop RL algorithms for robotics.

News

Jan 23, 2025 Our work Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning is accepted by ICLR 2025!

Latest Posts

Selected Publications

  1. ICLR
    Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
    Haoxin Lin, Yu-Yan Xu, Yihao Sun, Zhilong Zhang, Yi-Chen Li, Chengxing Jia, Junyin Ye, Jiaji Zhang, and Yang Yu
    In Proceedings of the 13th International Conference on Learning Representations, 2025
  2. AAAI
    Episodic Return Decomposition by Difference of Implicitly Assigned Sub-trajectory Reward
    Haoxin Lin, Hongqiu Wu, Jiaji Zhang, Yihao Sun, Junyin Ye, and Yang Yu
    In Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence, 2024
  3. ECAI
    Model-based Reinforcement Learning with Multi-step Plan Value Estimation
    Haoxin Lin*, Yihao Sun*, Jiaji Zhang, and Yang Yu
    In Proceedings of the 26th European Conference on Artificial Intelligence, 2023