多智能体强化学习，智能体博弈，智能体评估

团队招收硕士博士研究生、博士后、助理研究员、研发工程师、本科实习生，欢迎有机器学习、强化学习、博弈论等相关背景的同学与我联系。

欢迎访问团队官网（marl.ia.ac.cn）了解我们的研究方向、团队成员、研究成果等信息。

我们也在运营“及第”多智能体开源开放平台（jidiai.cn）和RLChina强化学习社区（rlchina.org），欢迎加入我们。

关于2023级招生：本团队与伦敦大学学院（UCL）紧密协作，欢迎对（多智能体）强化学习、博弈论等方向研究和研发感兴趣的夏令营同学与我联系，我们招收多位硕士、博士研究生，请发送简历至haifeng.zhang [at] ia.ac.cn，谢谢！

081104-模式识别与智能系统
081202-计算机软件与理论
081101-控制理论与控制工程

多智能体强化学习，博弈论，机制设计

2012-09--2018-07   北京大学   博士
2008-09--2012-07   北京大学   本科

2020-5~现在，中国科学院自动化研究所，副研究员、硕士生导师

2019-12~2020-5，北京大学前沿计算研究中心，访问学者

2018-12~2019-12，University College London（伦敦大学学院），Research Fellow（博士后）

   

[1] Jingqing Ruan, Yali Du, Xuantang Xiong, Xing, Dengpeng, Xiyun Li, Linghui Meng, Haifeng Zhang, Jun Wang, Bo Xu. GCS: Graph-Based Coordination Strategy for Multi-Agent Reinforcement Learning. International Joint Conference on Autonomous Agents and Multi-agent Systems (AAMAS)null. 2022, 
[2] Kuba, Jakub Grudzien, Wen, Muning, Yang, Yaodong, Meng, Linghui, Gu, Shangding, Zhang, Haifeng, Mguni, David Henry, Wang, Jun. Settling the Variance of Multi-Agent Policy Gradients. 2022, 
[3] Zhang Haifeng. Learning Correlated Communication Topology in Multi-agent Reinforcement Learning. AAMAS. 2021, 
[4] Zhang Haifeng. Signal Instructed Coordination in Team Competition. DAI. 2021, 
[5] Zhang Haifeng. Joint Caching and Transmission in the Mobile Edge Network: An Multi-Agent Learning Approach. Globecom. 2021, 
[6] Zhang Haifeng. Estimating α-Rank from A Few Entries with Low Rank Matrix Completion. ICML. 2021, 
[7] Liu, Yunfei, Yang, Yang, Chen, Xianyu, Shen, Jian, Zhang, Haifeng, Yu, Yong. Improving Knowledge Tracing via Pre-training Question Embeddings. 2020, http://arxiv.org/abs/2012.05031.

[8] Zhang Haifeng, Chen Weizhe, Huang Zeren, Li Minne, Yang Yaodong, Zhang Weinan, Wang Jun. Bi-level Actor-Critic for Multi-agent Coordination. 2020, http://arxiv.org/abs/1909.03510.

[9] Zhou, Xinyuan, Wu, Peng, Zhang, Haifeng, Guo, Weihong, Liu, Yuanchang. Learn to Navigate: Cooperative Path Planning for Unmanned Surface Vehicles Using Deep Reinforcement Learning. IEEE ACCESS[J]. 2019, 7: 165262-165278, https://doaj.org/article/7dc34cf1c408426c92f6a9031c0188cb.

[10] Zhang, Haifeng, Guo, Zilong, Zhang, Weinan, Cai, Han, Wang, Chris, Yu, Yong, Li, Wenxin, Wang, Jun. Layout Design for Intelligent Warehouse by Evolution With Fitness Approximation. IEEE ACCESS[J]. 2019, 7: 166310-166317, https://doaj.org/article/197860110a564ca096e11965684fd733.

[11] Zhou, Haoyu, Zhang, Haifeng, Zhou, Yushan, Wang, Xinchao, Li, Wenxin, Polycarpou, I, Read, JC, Andreou, P, Armoni, M. Botzone: An Online Multi-agent Competitive Platform for AI Education. ITICSE'18: PROCEEDINGS OF THE 23RD ANNUAL ACM CONFERENCE ON INNOVATION AND TECHNOLOGY IN COMPUTER SCIENCE EDUCATIONnull. 2018, 33-38, http://dx.doi.org/10.1145/3197091.3197099.

[12] Zhang, Yi, Huang, Houjun, Zhang, Haifeng, Ni, Liao, Xu, Wei, Ahmed, Nasir Uddin, Ahmed, Md Shakil, Jin, Yilun, Chen, Yingjio, Wen, Jingxuan, Li, Wenxin, IEEE. ICFVR 2017: 3rd International Competition on Finger Vein Recognition. 2017 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS (IJCB)null. 2017, 707-714, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000426973200086.

[13] Zhang Haifeng, Zhang Weinan, Rong Yifei, Ren Kan, Li Wenxin, Wang Jun, ACM. Managing Risk of Bidding in Display Advertising. WSDM'17: PROCEEDINGS OF THE TENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MININGnull. 2017, 581-590, http://dx.doi.org/10.1145/3018661.3018701.

[14] Ren Kan, Zhang Weinan, Rong Yifei, Zhang Haifeng, Yu Yong, Wang Jun, ACM. User Response Learning for Directly Optimizing Campaign Performance in Display Advertising. CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENTnull. 2016, 679-688, http://dx.doi.org/10.1145/2983328.2983347.

[15] 张海峰, 刘当一, 李文新. 通用对弈游戏：一个探索机器游戏智能的领域. 软件学报[J]. 2016, 2814-2827, http://lib.cqvip.com/Qikan/Article/Detail?id=670476756.

[16] Zhang Haifeng. Space-Consistent Game Equivalence Detection in General Game Playing. IJCAI 2015 Workshop on General Game Playing. 2015, 
[17] Zhang, Haifeng, Wang, Jun, Zhou, Zhiming, Zhang, Weinan, Wen, Ying, Yu, Yong, Li, Wenxin. Learning to Design Games: Strategic Environments in Deep Reinforcement Learning. http://arxiv.org/abs/1707.01310.

• 担任中国计算机学会（CCF）计算经济学专业组常务委员（www.ccf.org.cn/Chapters/TC/TC_Listing/TCCE/）。
• 担任 RLChina 学术委员会秘书长（rlchina.org）。
• 组织 1st Workshop on Evaluation in MARL（marl-evaluation.github.io）。
• 担任 IJTCS 2020/2021 MARL Track Chair（econcs.pku.edu.cn/ijtcs2020/IJTCS2020.html）。
• 组织 IJCAI 2020 麻将智能体竞赛（www.botzone.org.cn/static/gamecontest2020a_cn.html）。

（ 1 ） 大规模多智能体***系统, 负责人, 中国科学院计划, 2020-07--2023-06
（ 2 ） 原油***强化学习算法技术开发, 负责人, 企业委托, 2021-12--2023-06
（ 3 ） 多智能体系统***算法, 负责人, 国家任务, 2021-01--2023-12
（ 4 ） 分布式多智能体深度强化学习算法的评估方法, 负责人, 国家任务, 2023-01--2025-12