Biography

I am currently a tenure-track Assistant Professor and Presidential Young Fellow in the School of Data Science at The Chinese University of Hong Kong (Shenzhen). Previously, I worked as a Research Scientist (Huawei TopMind) in Huawei Noah Ark’s Lab from 2022-2024. I obtained my Ph.D. degree from the University of Alberta (2016-2022), under the supervision of Martin Müller and Dale Schuurmans. From 2020-2022, I also worked as a student researcher in Google Brain (now Google DeepMind), hosted by Bo Dai and Lihong Li.

My research interest is in the area of artificial intelligence and machine learning, especially reinforcement learning. I am particularly interested in applying machine learning techniques to solve complex sequential decision-making problems.

I am actively recruiting PhD students and research assistants. If you are interested in working with me, and with good programming skills and math background, you can contact me via email with your CV.

Publication

• Iteratively Refined Behavior Regularization for Offline Reinforcement Learning
  Yi Ma, Jianye HAO, Xiaohan Hu, Yan Zheng, Chenjun Xiao.
  Advances in Neural Information Processing Systems (NeurIPS), 2024.
  

  [arxiv]

• Diffusion Representation for Reinforcement Learning
  Dmitry Shribak, Chen-Xiao Gao, Yitong Li, Chenjun Xiao, Bo Dai.
  Advances in Neural Information Processing Systems (NeurIPS), 2024.
  

  [arxiv]

• Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration
  Hongming Zhang, Chenjun Xiao, Chao Gao, Han Wang, Bo Xu, Martin Müller.
  Advances in Neural Information Processing Systems (NeurIPS), 2024.
  

  [arxiv]

• HarmonyDream: Task Harmonization Inside World Models.
  Haoyu Ma, Jialong Wu, Ningya Feng, Chenjun Xiao, Dong Li, Jianye Hao, Jiamin Wang, and Mingsheng Long.
  International Conference on Machine Learning (ICML), 2024
  

  [arxiv]

• Rethinking Decision Transformer via Hierarchical Reinforcement Learning.
  Yi Ma, Jianye Hao, Hebin, Liang, and Chenjun Xiao.
  International Conference on Machine Learning (ICML), 2024
  

  [arxiv]

• Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation.
  Fengdi Che, Chenjun Xiao, Jincheng Mei, Bo Dai, Ramki Gummadi, Oscar Ramirez, Chris Harris, Rupam Mahmood, and Dale Schuurmans.
  International Conference on Machine Learning (ICML), Spotlight, 2024
  

  [arxiv]

• Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning.
  Hongming Zhang, Tongzheng Ren, Chenjun Xiao, Dale Schuurmans, and Bo Dai.
  International Conference on Machine Learning (ICML), 2024
  

  [arxiv]

• Multiagent Gumbel MuZero: Efficient Planning in Combinatorial Action Spaces.
  Xiaotian Hao, Jianye Hao, Chenjun Xiao, Kai Li, Dong Li, Yan Zheng.
  AAAI Conference on Artificial Intelligence (AAAI), 2024
  

  [paper]

• Energy-based Predictive Representations for Partially Observed Reinforcement Learning.
  Tianjun Zhang, Tongzheng Ren, Chenjun Xiao, Wenli Xiao, Joseph E. Gonzalez, Dale Schuurmans, Bo Dai.
  Conference on Uncertainty in Artificial Intelligence (UAI), 2023
  

  [paper]

• Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning.
  Xutong Zhao, Yangchen Pan, Chenjun Xiao, Sarath Chandar, Janarthanan Rajendran.
  Conference on Uncertainty in Artificial Intelligence (UAI), 2023
  

  [arxiv]

• The In-Sample Softmax for Offline Reinforcement Learning.
  Chenjun Xiao*, Han Wang*, Yangchen Pan, Adam White and Martha White.
  International Conference on Learning Representations (ICLR), Spotlight, 2023.
  

  [OpenReview]

• Latent Variable Representation for Reinforcement Learning.
  Tongzheng Ren*, Chenjun Xiao*, Tianjun Zhang, Na li, Zhaoran Wang, Sujay Sanghavi, Dale Schuurmans and Bo Dai.
  International Conference on Learning Representations (ICLR), 2023.
  

  [OpenReview]

• Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay
  Hongming Zhang, Chenjun Xiao, Han Wang, Jun Jin, Bo Xu, Martin Mueller.
  International Conference on Learning Representations (ICLR), 2023.
  

  [OpenReview]

• Understanding and Leveraging Overparameterization in Recursive Value Estimation.
  Chenjun Xiao, Bo Dai, Jincheng Mei, Oscar Ramirez, Ramki Gummadi, Chris Harris, and Dale Schuurmans.
  International Conference on Learning Representations (ICLR), 2022.
  

  [OpenReview]

• The Curse of Passive Data Collection in Batch ReinforcementLearning.
  Chenjun Xiao, Ilbin Lee, Bo Dai, Dale Schuurmans and Csaba Szepesvári.
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
  [arXiv]

• Understanding the Effect of Stochasticity in Policy Optimization.
  Jincheng Mei, Bo Dai, Chenjun Xiao, Csaba Szepesvári†, and Dale Schuurmans†.
  Advances in Neural Information Processing Systems (NeurIPS), 2021.
  

  [arXiv][OpenReview]

• On the Optimality of Batch Policy Optimization Algorithms.
  Chenjun Xiao*, Yifan Wu*, Tor Lattimore, Bo Dai, Jincheng Mei, Lihong Li, Csaba Szepesvári, and Dale Schuurmans.
  International Conference on Machine Learning (ICML), 2021.
  

  [arXiv]

• Escaping the Gravitational Pull of Softmax.
  Jincheng Mei, Chenjun Xiao, Bo Dai, Lihong Li, Csaba Szepesvári, and Dale Schuurmans.
  Advances in Neural Information Processing Systems (NeurIPS), Oral Presentation, 2020.
  

  [Paper]

• On the Global Convergence Rates of Softmax Policy Gradient Methods.
  Jincheng Mei, Chenjun Xiao, Csaba Szepesvári, and Dale Schuurmans.
  International Conference on Machine Learning (ICML), 2020.
  

  [arXiv]

• Learning to Combat Compounding-Error in Model-Based Reinforcement Learning.
  Chenjun Xiao, Yifan Wu, Chen Ma, Dale Schuurmans, Martin Mueller.
  NeurIPS 2019 Deep Reinforcement Learning Workshop.
  

  [Paper]

• Maximum Entropy Monte-Carlo Planning.
  Chenjun Xiao, Jincheng Mei, Ruitong Huang, Dale Schuurmans, Martin Müller.
  Advances in Neural Information Processing Systems (NeurIPS), 2019.
  

  [Paper][Poster]

• On Principled Entropy Exploration in Policy Optimization.
  Jincheng Mei, Chenjun Xiao, Ruitong Huang, Dale Schuurmans, Martin Müller.
  International Joint Conference on Artificial Intelligence (IJCAI), 2019.
  

  [Paper][Long version]

• Memory-Augmented Monte Carlo Tree Search,
  Chenjun Xiao, Jincheng Mei, Martin Müller.
  AAAI Conference on Artificial Intelligence (AAAI), 2018.
  Outstanding Paper Award
  

  [Paper]

• Factorization Ranking Model for Move Prediction in the Game of Go,
  Chenjun Xiao and Martin Müller.
  AAAI Conference on Artificial Intelligence (AAAI), 2016.
  

  [Paper]

• Only-One-Victor Pattern Learning in Computer Go,
  Jiao Wang, Chenjun Xiao, Tan Zhu, Chu-Husan Hsueh, Wen-Jie Tseng and I-Chen Wu.
  IEEE Transactions on Computational Intelligence and AI in Games, 2017.
  

  [Paper]

Other Links

Last Modified: 2024-06-10