Navigation
Institute of Automation, Chinese Academy of Sciences

Contact Us

Wechat

CN

Scan it
Wechat
Your current location：Home > People - Faculty&Staff
Kai LiAssociate Professor
  • E-mail：

    kai.li@ia.ac.cn

  • Address：

    1115 Automation Building, No. 95 Zhongguancun East Road, Haidian District, Beijing

  • Research Interests：

    Intelligent gaming, reinforcement learning, game AI

  • Website：

    https://kli-casia.github.io/

Biography :

Kai Li, an Associate Researcher at the Institute of Automation, Chinese Academy of Sciences, specializes in game decision intelligence and deep reinforcement learning. He received the Outstanding Award from the 2020 CCF-Tencent Rhino Bird Research Fund. Currently, he serves as the main lecturer for the "Principles and Applications of Computational Games" course at the University of the Chinese Academy of Sciences. He is responsible for several significant research tasks, including projects funded by the National Science Foundation of China, sub-projects of the Strategic Priority Research Program of the Chinese Academy of Sciences, and sub-projects of the National Key Research and Development Program of China. Kai Li has contributed to the academic community with over 20 publications in top-tier international journals and conferences such as NeurIPS, ICML, ICLR, AAAI, IJCAI, and AAMAS. He was honored with the Outstanding Paper Award at the AAAI 2022, a prestigious conference in artificial intelligence. Furthermore, he has successfully applied for and obtained more than 20 national invention patents. In recent years, his focus has been on addressing intelligent decision-making challenges in large-scale complex environments. He has developed a series of high-performance decision-making AIs and established the first large-scale imperfect information game research platform called OpenHoldem.

Publications :


  • Hang Xu, Kai Li, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. Dynamic Discounted Counterfactual Regret Minimization. ICLR 2024, Spotlight (Top 5%).
  • Yuheng Jing, Kai Li, Bingyun Liu, Yifan Zang, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. Towards Offline Opponent Modeling with In-context Learning. ICLR 2024.
  • Hang Xu, Kai Li, Bingyun Liu, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. PDCFR+: Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent. IJCAI 2024.
  • Jinmin He, Kai Li, Yifan Zang, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. Not All Tasks Are Equally Difficult: Multi-Task Reinforcement Learning with Dynamic Depth Routing. AAAI 2024.
  • Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement LearningYifan Zang, Jinmin He, Kai Li, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng.Neural Information Processing Systems (NeurIPS), 2023.
  • OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game ResearchKai Li, Hang Xu, Enmin Zhao, Zhe Wu, Junliang Xing.IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023.
  • Sample Efficient Reinforcement Learning Using Graph-Based Memory ReconstructionYongxin Kang, Enmin Zhao, Yifan Zang, Lijuan Li, Kai Li, Pin Tao, Junliang Xing.IEEE Transactions on Artificial Intelligence (TAI), 2023.
  • Sequential Cooperative Multi-Agent Reinforcement LearningYifan Zang, Jinmin He, Kai Li, Haobo Fu, Qiang Fu, Junliang Xing.International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023.
  • Greedy when Sure and Conservative when Uncertain about the OpponentsHaobo Fu, Ye Tian, Hongxiang Yu, Weiming Liu, Shuang Wu, Jiechao Xiong, Ying Wen, Kai Li, Junliang Xing, Qiang Fu, Wei YangInternational Conference on Machine Learning (ICML), 2022, Spotlight.
  • Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information GameHaobo Fu, Weiming Liu, Shuang Wu, Yijia Wang, Tao Yang, Kai Li, Junliang Xing, Bin Li, Bo Ma, Qiang Fu, Yang Wei.International Conference on Learning Representations (ICLR), 2022.
  • AutoCFR: Learning to Design Counterfactual Regret Minimization AlgorithmsHang Xu, Kai Li, Haobo Fu, Qiang Fu, Junliang Xing.AAAI Conference on Artificial Intelligence (AAAI), 2022, Oral.
  • AlphaHoldem: High-Performance Artificial Intelligence for Heads-Up No-Limit Poker via End-to-End Reinforcement LearningEnmin Zhao, Renye Yan, Jinqiu Li, Kai Li, Junliang Xing.AAAI Conference on Artificial Intelligence (AAAI), 2022. Distinguished Paper Award!
  • Exploration via State Influence ModelingYongxin Kang, Enmin Zhao, Kai Li, Junliang Xing.AAAI Conference on Artificial Intelligence (AAAI), 2021.
  • Potential Driven Reinforcement Learning for Hard Exploration TasksEnmin Zhao, Shihong Deng, Yifan Zang, Yongxin Kang, Kai Li, Junliang Xing.International Joint Conference on Artificial Intelligence (IJCAI), 2020.
  • Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age EstimationKai Li, Junliang Xing, Chi Su, Weiming Hu, Yundong Zhang, Stephen Maybank.IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
  • D2C: Deep Cumulatively and Comparatively Learning for Human Age EstimationKai Li, Junliang Xing, Weiming Hu, Stephen J Maybank.Pattern Recognition, 2017.
  • Diagnosing Deep Learning Models for High Accuracy Age Estimation from a Single ImageJunliang Xing, Kai Li, Weiming Hu, Chunfeng Yuan, Haibin Ling.Pattern Recognition, 2017.
  • Predicting Image Memorability by Multi-View Adaptive RegressionHouwen Peng, Kai Li, Bing Li, Haibin Ling, Weihua Xiong, Weiming Hu.ACM International Conference on Multimedia (ACM Multimedia), 2015.


Awards :

  • AAAI 2022 Outstanding Paper Award at the Top Conference on Artificial Intelligence
  • Second prize in the 2021 National Air Game Competition
  • 2020 CCF - Tencent Rhinoceros Bird Fund Excellence Award
  • 2020 Tencent King of Glory Enlightenment Inviting Season Army

Efficient Intelligent Computing and Learning Address：95 Zhongguancun East Road, Haidian District, Beijing E-mail：clab@ia.ac.cn 京ICP备05002829号-1