李凯  中国科学院自动化研究所  副研究员  硕士研究生导师

复杂系统认知与决策重点实验室   高效智能计算与学习团队 

电子邮件： kai.li@ia.ac.cn

通信地址： 北京市海淀区中关村东路95号自动化大厦1123室

邮政编码： 100190

个人网站： https://kli-casia.github.io/

个人介绍

李凯，中国科学院自动化研究所副研究员，硕士生导师，研究领域为博弈决策智能、深度强化学习、大模型、AI4Science等，负责国家自然科学基金、中国科学院战略性先导科技专项课题、新一代人工智能国家科技重大专项子课题等多项重要科研任务，在包括CCF-A类期刊会议（如AI、NeurIPS、ICML、ICLR、AAAI、IJCAI等）上发表学术论文30余篇，获人工智能顶级会议AAAI 2022卓越论文奖，获2020 CCF-腾讯犀牛鸟科研基金优秀奖，申请/授权国家发明专利20余项，获多次国际竞赛冠军，长期担任中国科学院大学研究生专业核心课程《计算博弈原理与应用》主讲教师，在非完备信息博弈、多智能体系统、智能视觉感知等方面具有丰富的研究与应用经验，近年来围绕大规模复杂博弈环境下的智能决策问题，研发了一系列高水平决策AI，并构建了学界首个大规模非完备信息博弈开放研究平台。

招生信息

招收对决策智能、AI4Science等方向感兴趣的硕士研究生。希望你具备良好的数学、编程和英语基础，踏实肯干的精神和乐观积极的心态。

对学生的培养侧重基础学术研究，团队算力资源充沛，鼓励学生自主开展前沿的研究课题，发表高水平国际学术论文。

本人与国内头部企业如腾讯AI Lab等一直保持密切合作，鼓励学生开展实习交流。

欢迎计算机等相关专业的学生联系报考，由于招生数量有限，请提前与我联系。

长期招收科研实习生（高年级本科生、低年级硕博生等），参与国家级项目，发表高水平论文，可推荐读研、读博、工作。


招生专业
081104-模式识别与智能系统

教育背景

2013-09--2018-06   中国科学院自动化研究所模式识别国家重点实验室   工学博士
2009-09--2013-06   大连理工大学   工学学士

工作经历

2020-01--现在, 中国科学院自动化研究所, 副研究员
2018-07--2019-12,中国科学院自动化研究所, 助理研究员

教授课程

计算博弈原理与应用

发表论文

近期发表的论文如下：

  • Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning. Hanlin Yang, Jian Yao, Weiming Liu, Qing Wang, Hanmin Qin, Kong hansheng, Kirk Tang, Jiechao Xiong, Chao Yu, Kai Li, Junliang Xing, Hongwu Chen, Juchao Zhuo, Qiang Fu, Yang Wei, Haobo Fu. International Conference on Learning Representations (ICLR), 2025.

  • An Open-Ended Learning Framework for Opponent Modeling. Yuheng Jing, Kai Li, Bingyun Liu, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. AAAI Conference on Artificial Intelligence (AAAI), 2025, Oral, Top 5%. (Corresponding Author)

  • Automatically Designing Counterfactual Regret Minimization Algorithms for Solving Imperfect-Information Games. Kai Li, Hang Xu, Haobo Fu, Qiang Fu, Junliang Xing. Artificial Intelligence (AI), 2024.

  • Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance. Jinmin He, Kai Li, Yifan Zang, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. Neural Information Processing Systems (NeurIPS), 2024. (Corresponding Author)

  • Opponent Modeling with In-context Search. Yuheng Jing, Bingyun Liu, Kai Li, Yifan Zang, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. Neural Information Processing Systems (NeurIPS), 2024. (Corresponding Author)

  • Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent. Hang Xu, Kai Li, Bingyun Liu, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. International Joint Conference on Artificial Intelligence (IJCAI), 2024. (Corresponding Author)

  • Towards Offline Opponent Modeling with In-context Learning. Yuheng Jing, Kai Li, Bingyun Liu, Yifan Zang, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. International Conference on Learning Representations (ICLR), 2024. (Corresponding Author)

  • Dynamic Discounted Counterfactual Regret Minimization. Hang Xu, Kai Li, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. International Conference on Learning Representations (ICLR), 2024, Spotlight, Top 5%. (Corresponding Author)

  • Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing. Jinmin He, Kai Li, Yifan Zang, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. AAAI Conference on Artificial Intelligence (AAAI), 2024. (Corresponding Author)

  • Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning. Yifan Zang, Jinmin He, Kai Li, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng. Neural Information Processing Systems (NeurIPS), 2023. (Corresponding Author)

  • OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research. Kai 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 Reconstruction. Yongxin 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 Learning. Yifan 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 Opponents. Haobo Fu, Ye Tian, Hongxiang Yu, Weiming Liu, Shuang Wu, Jiechao Xiong, Ying Wen, Kai Li, Junliang Xing, Qiang Fu, Wei Yang. International Conference on Machine Learning (ICML), 2022, Spotlight.

  • Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game. Haobo 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 Algorithms. Hang 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 Learning. Enmin Zhao, Renye Yan, Jinqiu Li, Kai Li, Junliang Xing. AAAI Conference on Artificial Intelligence (AAAI), 2022. Distinguished Paper Award!

  • Exploration via State Influence Modeling. Yongxin Kang, Enmin Zhao, Kai Li, Junliang Xing. AAAI Conference on Artificial Intelligence (AAAI), 2021.

  • Potential Driven Reinforcement Learning for Hard Exploration Tasks. Enmin Zhao, Shihong Deng, Yifan Zang, Yongxin Kang, Kai Li, Junliang Xing. International Joint Conference on Artificial Intelligence (IJCAI), 2020.

  • ...

科研项目

  1. 复杂问题智能化建模方法，中科院A类先导科技专项课题，负责人，2024.11~2026.10​

  2. 知识数据混合驱动双向演化学习与应用验证，中科院A类先导科技专项子课题，负责人，2020.07~2025.06

  3. 非规则对抗的博弈理论与智能方法，新一代人工智能国家科技重大专项课题，子课题负责人，2023.01~2025.12

  4. 对抗态势感知基础理论和关键技术研究，科技创新2030“新一代人工智能”重大项目课题，核心骨干，2020.07~2023.06

指导学生

指导学生

  • 2023-，汤月龙，硕士研究生

  • 2023-，华恒鑫，硕士研究生

  • 2023-，许一，硕士研究生

  • 2024-，张紫闻，硕士研究生

  • 2025-，顾胜达，硕士研究生


联合指导学生

  • 2018-2023，赵恩民，博士研究生

  • 2018-2023，康永欣，博士研究生

  • 2019-，臧一凡，博士研究生

  • 2020-，徐航，博士研究生

  • 2021-，何金岷，博士研究生

  • 2022-，景煜恒，博士研究生

  • 2018-2021，张蒙，硕士研究生

  • 2019-2022，吴哲，硕士研究生