Wanpeng Zhang (张万鹏)

Currently, I am a Ph.D. candidate in the School of Computer Science at Peking University , advised by Prof. Zongqing Lu. My research interests include Reinforcement Learning, Generative Modeling, Multimodal LLMs. Feel free to contact me if you are interested in discussing or collaborating.
[Email / Google Scholar / DBLP / Github / CV]

Education

• School of Computer Science, Peking University.
  • Ph.D. Candidate. Advised by Prof. Zongqing Lu.
  • 2022 — Now
• Department of Computer Science and Technology, Tsinghua University.
  • M.Sc. Degree. Advised by Prof. Xi Xiao.
  • 2019 — 2022
• School of Mathematical Sciences, Nankai University.
  • B.Sc. Degree.
  • 2015 — 2019

Publication

• Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation. (ICML’24)
  • Wanpeng Zhang, Yilin Li, Boyu Yang, Zongqing Lu.
  • Link / PDF / BibTeX
• AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback. (NAACL’24)
  • Wanpeng Zhang, Zongqing Lu.
  • Link / PDF / BibTeX / Code
• Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning. (ICML’23)
  • Ziluo Ding*, Wanpeng Zhang*, Junpeng Yue, Xiangjun Wang, Tiejun Huang, Zongqing Lu. *equal contribution
  • Link / PDF / BibTeX / Code / Talk
• Model-Based Opponent Modeling. (NeurIPS’22)
  • Xiaopeng Yu, Jiechuan Jiang, Wanpeng Zhang, Haobin Jiang, Zongqing Lu.
  • Link / PDF / BibTeX / Code / Talk
• iGrow: A Smart Agriculture Solution to Autonomous Greenhouse Control. (AAAI’22)
  • Xiaoyan Cao, Yao Yao, Lanqing Li, Wanpeng Zhang, Zhicheng An, Zhong Zhang, Shihui Guo, Li Xiao, Xiaoyu Cao, Dijun Luo.
  • Link / PDF / BibTeX / Code
• Efficient and Stable Information Directed Exploration for Continuous Reinforcement Learning. (ICASSP’22)
  • Mingzhe Chen, Xi Xiao, Wanpeng Zhang, Xiaotian Gao.
  • Link / PDF / BibTeX
• Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control. (ACML’21)
  • Wanpeng Zhang, Xiaoyan Cao, Yao Yao, Zhicheng An, Dijun Luo, Xi Xiao.
  • Link / PDF / BibTeX / Talk
• Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation. (ICRA’21)
  • Yao Yao, Li Xiao, Zhicheng An, Wanpeng Zhang, Dijun Luo.
  • Link / PDF / BibTeX / Code
• A Simulator-based Planning Framework for Optimizing Autonomous Greenhouse Control Strategy. (ICAPS’21)
  • Zhicheng An, Xiaoyan Cao, Yao Yao, Wanpeng Zhang, Lanqing Li, Yue Wang, Shihui Guo, Dijun Luo.
  • Link / PDF / BibTeX
• Self-Paced Probabilistic Principal Component Analysis for Data with Outliers. (ICASSP’20)
  • Bowen Zhao, Xi Xiao, Wanpeng Zhang, Bin Zhang, Guojun Gan, Shutao Xia.
  • Link / PDF / BibTeX / Code

Preprint

• MBDP: A Model-based Approach to Achieve both Robustness and Sample Efficiency via Double Dropout Planning. (arXiv’21.08)
  • Wanpeng Zhang, Xi Xiao, Yao Yao, Mingzhe Chen, Dijun Luo.
  • Link / PDF / BibTeX

Patent

• Method, device and equipment for determining parameters and storage medium. (CN112527104A)
  • Wanpeng Zhang, Dijun Luo, Xi Xiao
  • Link / PDF

Experience

• Beijing Academy of Artificial Intelligence (BAAI)
  • Research Intern
  • 2024.05 — Now
• Tencent AI Lab
  • Research Intern
  • 2020.06 — 2021.07
• Availink
  • Research Intern
  • 2018.08 — 2018.10

Academic Service

• Conference Reviewer
  • ICML 2022, 2023, 2024
  • NeurIPS 2022, 2023, 2024
  • ICLR 2024