李斯源
副教授/硕士生导师
研究方向
联系方式
电子邮箱：siyuanli@hit.edu.cn
个人简介
李斯源，博士，副教授，硕导，就职于哈尔滨工业大学计算学部模式识别与智能系统研究中心。主要研究方向为具身智能、深度强化学习、多智能体系统等。在CCF A/B类会议和期刊上发表20余篇高水平学术论文，授权发明专利3项。获得2023年度CCF多智能体学组优秀博士生论文奖。担任中国指挥与控制学会空间信息通信技术专委会执行委员，多次担任NeurIPS, ICML, IJCAI等CCF A类会议审稿人，作为负责人承担国家自然科学基金青年基金。
英文主页：https://siyuanlee.github.io/
教育经历
2017.09-2022.06清华大学，交叉信息研究院，计算机科学与技术专业，工学博士学位
2013.09-2017.06北京邮电大学，信息与通信工程学院，通信工程专业，工学学士学位
论文发表
[1]Siyuan Li, Xun Wang, Rongchang Zuo, Kewu Sun, Lingfei Cui, Jishiyu Ding, Peng Liu and Zhe Ma. Robust Visual Imitation Learning with Inverse Dynamics Representations.The Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024 [CCF A类]
[2]Siyuan Li, Hao Li, Jin Zhang, Zhen Wang, Peng Liu and Chongjie Zhang. IOB: integrating optimization transfer and behavior transfer for multi？policy reuse.Autonomous Agents and Multi-Agent Systems (JAAMAS), 2023 [CCF B类]
[3]Shijie Han, Siyuan Li, Bo An, Wei Zhao and Peng Liu. Classifying Ambiguous Identities in Stochastic Games with Multi-Agent Reinforcement Learning.Autonomous Agents and Multi-Agent Systems (JAAMAS), 2023 [CCF B类]
[4]Rushuai Yang, Chenjia Bai, Hongyi Guo, Siyuan Li, Bin Zhao, Zhen Wang, Peng Liu and Xuelong Li. Behavior Contrastive Learning for Unsupervised Skill Discovery.International Conference on Machine Learning (ICML), 2023 [CCF A类]
[5]Yiqin Yang, Hao Hu, Wenzhe Li, Siyuan Li, Jun Yang, Qianchuan Zhao and Chongjie Zhang. Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery.The Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023 [CCF A类]
[6]Ruiqi Zhu, Siyuan Li, Tianhong Dai, Chongjie Zhang and Oya Celiktutan. Learning to Solve Tasks with Incomplete Demonstration.International Conference on Intelligent Robots and Systems (IROS), 2023. [CCF C类]
[7]Siyuan Li, Jin Zhang, Jianhao Wang, Yang Yu and Chongjie Zhang. Active Hierarchical Exploration with Stable Subgoal Representation Learning.The Tenth International Conference on Learning Representations (ICLR), 2022 [TH-CPL A类]
[8]Jin Zhang, Siyuan Li and Chongjie Zhang. CUP: Critic-Guided Policy Reuse.Advances in Neural Information Processing Systems (NeurIPS), 2022 [CCF A类]
[9]Hui Niu*, Siyuan Li* and Jian Li. MetaTrader: A Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization.International Conference on Information and Knowledge Management (CIKM), 2022 [CCF B类]
[10]Siyuan Li*, Lulu Zheng*, Jianhao Wang and Chongjie Zhang. Learning Subgoal Representations with Slow Dynamics.The Ninth International Conference on Learning Representations (ICLR), 2021 [TH-CPL A类]
[11]Jianhao Wang*, Wenzhe Li*, Haozhe Jiang, Guangxiang Zhu, Siyuan Li and Chongjie Zhang. Offline Reinforcement Learning with Reverse Model-based Imagination.Advances in Neural Information Processing Systems (NeurIPS), 2021 [CCF A类]
[12]Siyuan Li. Deep Reinforcement Learning with Hierarchical Structures.The Thirtieth International Joint Conference on Artificial Intelligence (IJCAI) Doctoral Consortium, 2021
[13]Siyuan Li*, Rui Wang*, Minxue Tang and Chongjie Zhang. Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards.Advances in Neural Information Processing Systems (NeurIPS), 2019 [CCF A类]
[14]Siyuan Li, Fangda Gu, Guangxiang Zhu and Chongjie Zhang. Context-Aware Policy Reuse.International Conference on Autonomous Agents and MultiAgent Systems (AAMAS), 2019 [CCF B类]
[15]Siyuan Li and Chongjie Zhang. An Optimal Online Method of Selecting Source Policies for Reinforcement Learning.The Thirty-Second AAAI Conference on Artificial Intelligence, 2018 [CCF A类]
[16]Hui Niu*, Siyuan Li*, Jian Li and Jian Guo. Deep Reinforcement Learning with Multi-Granularity Predictive Signals for Optimal Market Making.Under review.
[17]Siyuan Li, Hui Niu, Jiahao Zheng, Zhouchi Lin, Jian Li, Jian Guo and Zhen Wang. Toward Automatic Market Making: An Imitative Reinforcement Learning Approach with Predictive Representation Learning.Under review on IEEE Transactions on Emerging Topics in Computational Intelligence.
[18]Yongyan Wen, Siyuan Li, Bo An, Wei Zhao and Peng Liu. Curriculum Reinforcement Learning with Measurable Task Representation Learning.Under review on ACM Transactions on Intelligent Systems and Technology.
[19]李斯源，左镕畅，王鑫淼，赵英男.面向无人机近距离空战问题的高模仿性强化学习控制方法.《计算级工程》期刊在审.
