Bio

Haifeng Zhang is an associate professor at Institute of Automation, Chinese Academy of Sciences (CASIA), leading the Collective Decision Intelligence Lab. His research areas include reinforcement learning, game AI, game theory and computational advertising. Before joining CASIA, he was a visiting scientist at Center on Frontiers of Computing Studies (CFCS), Peking University. Earlier, he was a research fellow at University College London. He received his PhD in computer science and his bachelor’s degrees in computer science and economics from Peking University.

Publications

• Chen Wang, Yan Song, Shuai Wu, Sa Wu, Ruizhi Zhang, Shu Lin, Haifeng Zhang. “AI-Olympics: Exploring the Generalization of Agents through Open Competitions.” [IJCAI 2024]
• Yongcheng Zeng, Guoqing Liu, Weiyu Ma, Ning Yang, Haifeng Zhang, Jun Wang. “Token-level Direct Preference Optimization.” [ICML 2024]
• Xinyu Cui, Boai Sun, Yi Zhu, Ning Yang, Haifeng Zhang, Weicheng Cui, Dixia Fan, Jun Wang. “Enhancing efficiency and propulsion in bio-mimetic robotic fish through end-to-end deep reinforcement learning.” [Physics of Fluids 2024] (featured article, reported by AIP Scilight)
• Yan Song, He Jiang, Haifeng Zhang, Zheng Tian, Weinan Zhang, Jun Wang. “Boosting Studies of Multi-Agent Reinforcement Learning on Google Research Football Environment: the Past, Present, and Future.” [AAMAS 2024b]
• Qirui Mi, Siyu Xia, Yan Song, Haifeng Zhang, Shenghao Zhu, Jun Wang. “TaxAI: A Dynamic Economic Simulator and Benchmark for Multi-Agent Reinforcement Learning.” [AAMAS 2024a]
• Xue Yan, Jiaxian Guo, Xingzhou Lou, Jun Wang, Haifeng Zhang, Yali Du. “An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination.” [NeurIPS 2023]
• Yan Song, He Jiang, Zheng Tian, Haifeng Zhang, Yingping Zhang, Jiangcheng Zhu, Zonghong Dai, Weinan Zhang, Jun Wang. “An Empirical Study on Google Research Football Multi-agent Scenarios.” [Machine Intelligence Research 2022b]
• Linghui Meng, Muning Wen, Chenyang Le, Xiyun Li, Dengpeng Xing, Weinan Zhang, Ying Wen, Haifeng Zhang, Jun Wang, Yaodong Yang, Bo Xu. “Offline Multi-agent Decision Transformer.” [Machine Intelligence Research 2022a]
• Bo Liu, Xidong Feng, Jie Ren, Luo Mai, Rui Zhu, Haifeng Zhang, Jun Wang, Yaodong Yang. “A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning.” [NeurIPS 2022]
• Jingqing Ruan, Yali Du, Xuantang Xiong, Dengpeng Xing, Xiyun Li, Linghui Meng, Haifeng Zhang, Jun Wang and Bo Xu. “GCS: Graph-Based Coordination Strategy for Multi-Agent Reinforcement Learning.” [AAMAS 2022]
• Xue Yan, Yali Du, Binxin Ru, Jun Wang, Haifeng Zhang, Xu Chen. “Learning to Identify Top Elo Ratings as A Dueling Bandits Problem.” [AAAI 2022]
• Chenguang Wang, Yaodong Yang, Oliver Slumbers, Congying Han, Tiande Guo, Haifeng Zhang, Jun Wang. “A Game-theoretic Approach for Improving Generalization Ability of TSP Solvers.” [arXiv 2021]
• Liheng Chen, Hongyi Guo, Haifeng Zhang, Fei Fang, Yaoming Zhu, Ming Zhou, Qing Wang, Weinan Zhang, Yong Yu. “Signal Instructed Coordination in Team Competition.” [DAI 2021]
• Jakub Grudzien Kuba, Muning Wen, Yaodong Yang, Linghui Meng, Shangding Gu, Haifeng Zhang, David Henry Mguni, Jun Wang. “Settling the Variance of Multi-Agent Policy Gradients.” [NeurIPS 2021]
• Qirui Mi, Ning Yang, Haifeng Zhang, Haijun Zhang, Jun Wang. “Joint Caching and Transmission in the Mobile Edge Network: An Multi-Agent Learning Approach.” [Globecom 2021]
• Yali Du, Xue Yan, Xu Chen, Jun Wang, Haifeng Zhang. “Estimating α-Rank from A Few Entries with Low Rank Matrix Completion.” [ICML 2021]
• Yali Du, Bo Liu, Vincent Moens, Ziqi Liu, Zhicheng Ren, Jun Wang, Xu Chen, Haifeng Zhang. “Learning Correlated Communication Topology in Multi-Agent Reinforcement Learning.” [AAMAS 2021]
• 张伟楠，张海峰. “多智能体强化学习研究与实践.” [中国人工智能学会通讯 2020年第7期]
• 张伟楠，任侃，张海峰. “计算广告中的机器学习问题与方法.” [中国计算机学会通讯 2020年第5期]
• Yunfei Liu, Yang Yang, Xianyu Chen, Jian Shen, Haifeng Zhang, Yong Yu. “Improving Knowledge Tracing via Pre-training Question Embeddings.” [IJCAI 2020]
• Haifeng Zhang, Weizhe Chen, Zeren Huang, Minne Li, Yaodong Yang, Weinan Zhang, Jun Wang. “Bi-level Actor-Critic for Multi-agent Coordination.” [AAAI 2020]
• Haifeng Zhang, Zilong Guo, Han Cai, Chris Wang, Weinan Zhang, Yong Yu, Wenxin Li, Jun Wang. “Layout Design for Intelligent Warehouse by Evolution with Fitness Approximation.” [IEEE Access 2019b]
• Xinyuan Zhou, Peng Wu, Haifeng Zhang, Weihong Guo, Yuanchang Liu. “Learn to Navigate: Cooperative Path Planning for Unmanned Surface Vehicles Using Deep Reinforcement Learning.” [IEEE Access 2019a]
• Haifeng Zhang, Jun Wang, Zhiming Zhou, Weinan Zhang, Ying Wen, Yong Yu, Wenxin Li. “Learning to Design Games: Strategic Environments in Deep Reinforcement Learning.” [IJCAI 2018]
• Haoyu Zhou, Haifeng Zhang, Yushan Zhou, Xinchao Wang, and Wenxin Li. “Botzone: an Online Multi-agent Competitive Platform for AI Education.” [ITiCSE 2018]
• Yi Zhang, Houjun Huang, Haifeng Zhang, Ni Liao and Wenxin Li. “ICFVR 2017: 3rd International Competition on Finger Vein Recognition.” [IJCB 2017]
• Haifeng Zhang, Weinan Zhang, Yifei Rong, Kan Ren, Wenxin Li, Jun Wang. “Managing Risk of Bidding in Display Advertising.” [WSDM 2017]
• Kan Ren, Weinan Zhang, Yifei Rong, Haifeng Zhang, Yong Yu, and Jun Wang. “User Response Learning for Directly Optimizing Campaign Performance in Display Advertising.” [CIKM 2016]
• 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 2016]
• Haifeng Zhang, Dangyi Liu, and Wenxin Li. “Space-Consistent Game Equivalence Detection in General Game Playing.” [IJCAI 2015 Workshop on General Game Playing]
• Shu Lin, Qinjian Zhang, and Haifeng Zhang. “Object Representation in Angry Birds Game.” [IJCAI 2013 Angry Birds AI Competition]
• Haifeng Zhang, Ge Gao, Wenxin Li, Cheng Zhong, Wenyuan Yu, Cheng Wang. “Botzone: A Game Playing System for Artificial Intelligence Education.” [FECS 2012]

Projects

• Founder of Jidi, an online AI competition and evaluation platform.
• First author of botzone.org, an online game AI competition platform obtaining 8000+ active users, 58000+ bots and more than 19 million game records since 2014 and widely applied by 10+ top universities (PKU, THU, etc), top algorithm competitions (NOI, ACM/ICPC) and top IT companies (Microsoft).
• Author of General Game Player, a general game AI designed to play any game described by the Game Description Language (GDL).

Awards

• Award for Scientific Research of PKU (2015)
• Miaozhen Academic Scholarship (2013)
• IBM Academic Scholarship (2011)
• Tencent Academic Scholarship (2010)
• Gold Medal of ACM/ICPC Regional Contest in Asia (Wuhan) (2009)
• First Prize of Peking University Mathematical Modeling Contest (2009)

Services

• Reviewer for AAAI, IJCAI, TNNLS, Acta Automatica Sinica, etc.
• Secretary General for RLChina
• Co-chair for DAI 2020 Workshop on Evaluation in Multi-agent Reinforcement Learning
• Co-chair for [IJTCS 2020/2021 Multi-agent Reinforcement Learning Track]
• Co-chair for IJCAI 2020 Majhong Competition
• Teaching assistant at University College London on Multi-agent Artificial Intelligence (2019)
• Teaching assistant at Peking University, including Algorithms in Game AI (2018), General Game Playing (2015), Algorithm Analysis (2013, 2014), Data Structure and Algorithm (2013) and Introduction to Artificial Intelligence (2013)
• Designer and organizer of AI competition as a part of National Olympiad in Informatics (NOI) in China (2010, 2011, 2012)