Zongzhang Zhang @ NJU-AI

Full Publication List

2026

• Jing-Cheng Pang, Kaiyuan Li, Pengyuan Wang, Xiong-Hui Chen, Jiacheng Xu, Zongzhang Zhang, and Yang Yu. Language Model Self-Improvement by Reinforcement Learning Contemplation without External Supervision. Journal of Artificial Intelligence Research, 86, Article 13, 31 pages, June 2026. [Paper]
• Enguang Yao, Qidong Liu, Jiajia Hou, Mingfei Sun, Zongzhang Zhang, and Mingliang Xu. LaTac: Latent Tactics for Robust Multi-agent Coordination under Intermittent Communication. SCIENCE CHINA Information Sciences, 2026, 69(7): 179101:1-179101:2. [Paper]
• Zhikai Zhang, Chao Chen, Han Xue, Jilong Wang, Sikai Liang, Yun Liu, Zongzhang Zhang, He Wang, and Li Yi. Unleashing Humanoid Reaching Potential via Real-World-Ready Skill Space. IEEE Robotics and Automation Letters, 2026, 11(2): 2082-2089. [Paper] [Code] [Project Page]
This work also appeared in: CoRL 2025 Workshop on Learning Effective Abstractions for Planning, Seoul, Korea, 2025.
• Wenjie Qiu, Yi-Chen Li, Xuqin Zhang, Tianyi Zhang, Yihang Zhang, Zongzhang Zhang, and Yang Yu. Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference. Frontiers of Computer Science. DOI:10.1007/s11704-026-51483-4. [Paper]
• Xiaoxia Wang, Xiaoyan Zhou, Dong Zhang, Zongzhang Zhang, Yushun Gong, Zhengzhi Feng, and Jingming Hou. The Prefrontal-Striatal Signatures of Reduced Model-Based Learning in Depressed Patients. Annals of General Psychiatry, 2026, 25, Article Number 11: 1-16. [Paper]
• Aoran Wang, Lei Ou, Yang Yu, and Zongzhang Zhang. Reward Model Evaluation via Automatically-Ranked Policy Alignment. In: Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI-2026), pages 26124-26132, Singapore, 2026. [Paper] [Appendix] [Video/Poster/Slides]
• Tao Jiang, Zichuan Lin, Lihe Li, Yi-Chen Li, Cong Guan, Lei Yuan, Zongzhang Zhang, Yang Yu, and Deheng Ye. Multi-Agent In-Context Coordination via Decentralized Memory Retrieval. In: Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI-2026), pages 22363-22371, Singapore, 2026. [Paper] [Code & Appendix] [Video/Poster/Slides]
• Pengfei Liu, Rui Kong and Zongzhang Zhang. Efficient Preference Alignment via Pareto Exploration (Student Abstract). In: Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI-2026), pages 41281-41283, Singapore, 2026. [Paper] [Appendix] [Video/Poster]
• Lianghui Liu and Zongzhang Zhang. Meta-Normalizing Flow for Data-Limited Offline Meta-Reinforcement Learning (Student Abstract). In: Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI-2026), pages 41278-41280, Singapore, 2026. [Paper] [Appendix]
• Di Xue, Jing Jiang, Shaowei Zhang, Wenhao Guo, Lei Yuan, Zongzhang Zhang, and Yang Yu. Learning Disentangled Multi-Agent World Model for Decentralized Control. In: Proceedings of the 43rd International Conference on Machine Learning (ICML-2026), Seoul, South Korea, 2026.
• Chenyang Wu, Tianyu Wang, Shengjun Fang, Mingjun Cao, Pengfei Liu, Zongzhang Zhang, Yeshu Li, Zhilin Zhang, Chuan Yu, Jian Xu, and Bo Zheng. Physics-Informed Generative World Models for Real-Time Bidding: Deriving Statistical Laws from First Principles. In: Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD-2026), Jeju, Korea, 2026.
• Wenjie Qiu, Xuqin Zhang, Yihang Zhang, Aoran Wang, Zongzhang Zhang, and Yang Yu. RMEval: Bridging Reward Model Evaluation and Policy Evaluation through Ranking Consistency. In: Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD-2026), Jeju, Korea, 2026.

2025

• Yi-Chen Li, Ningjing Chao, Zongzhang Zhang, Fuxiang Zhang, Lei Yuan, and Yang Yu. Generalizable Multi-Modal Adversarial Imitation Learning for Non-stationary Dynamics. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47(7): 5600-5612. [Paper]
• Hao Ding, Chengxing Jia, Zongzhang Zhang, Cong Guan, Feng Chen, Lei Yuan, and Yang Yu. Learning to Coordinate with Different Teammates via Team Probing. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(9): 15807-15821. [Paper]
• Fuxiang Zhang, Junyou Li, Yi-Chen Li, Zongzhang Zhang, Yang Yu, and Deheng Ye. Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(11): 19681-19692. [Paper]
• Cong Guan, Feng Chen, Lei Yuan, Zongzhang Zhang, and Yang Yu. Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-Agent Reinforcement Learning. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(5): 9044-9056. [Paper] [Code]
• Feng Chen, Xinwei Chen, Rong-Jun Qin, Cong Guan, Lei Yuan, Zongzhang Zhang, and Yang Yu. Efficient Multi-Agent Cooperation Learning through Teammate Lookahead. Transactions on Machine Learning Research, 2025, 03: 1-27. [Paper]
• Cong Guan, Tao Jiang, Yi-Chen Li, Zongzhang Zhang, Lei Yuan, and Yang Yu. Constraining an Unconstrained Multi-Agent Policy with Offline Data. Neural Networks, 2025, 186: 107253. [Paper]
• Yi-Chen Li, Fuxiang Zhang, Wenjie Qiu, Lei Yuan, Chengxing Jia, Zongzhang Zhang, Yang Yu, and Bo An. Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation. In: Proceedings of the 13th International Conference on Learning Representations (ICLR-2025), Singapore, 2025. [Paper] [Code]
• Chen-Xiao Gao, Chenyang Wu, Mingjun Cao, Chenjun Xiao, Yang Yu, and Zongzhang Zhang. Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning. In: Proceedings of the 42nd International Conference on Machine Learning (ICML-2025), pages 18630-18657, Vancouver, Canada, 2025. [Paper] [Code] [Project Page]
• Shihan Dou, Jiayi Chen, Chenhao Huang, Feng Chen, Wei Chengzhi, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, and Xuanjing Huang. Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL-2025), pages 5710–5728, Vienna, Austria, 2025. [Paper]
• Lei Song, Chen-Xiao Gao, Ke Xue, Chenyang Wu, Dong Li, Jianye Hao, Zongzhang Zhang, and Chao Qian. Reinforced In-Context Black-Box Optimization. In: Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI-2025), pages 8939-8947, Montreal, Canada, 2025. [Paper]
• Rui Yu, Shenghua Wan, Yucen Wang, Chen-Xiao Gao, Le Gan, Zongzhang Zhang, and De-Chuan Zhan. Reward Models in Deep Reinforcement Learning: A Survey. In: Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI-2025), pages 10807-10816, Montreal, Canada, 2025. [Paper]
• Jiahui Wang, Chao Chen, Jiacheng Xu, Zongzhang Zhang, and Yang Yu. Focus-Then-Reuse: Fast Adaptation in Visual Perturbation Environments. In: Advances in Neural Information Processing Systems 38 (NeurIPS-2025), pages 27860-27891, San Diego, USA, 2025. [Paper] [Code]
• Shihan Dou, Ming Zhang, Chenhao Huang, Jiayi Chen, Feng Chen, Shichun Liu, Yan Liu, Chenxiao Liu, Cheng Zhong, Zongzhang Zhang, Tao Gui, Chao Xin, Chengzhi Wei, Lin Yan, Qi Zhang, and Xuanjing Huang. EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving. In: Advances in Neural Information Processing Systems 38 (NeurIPS-2025), pages 125892-125945, San Diego, USA, 2025. [Paper] [Code]
• Yi-Chen Li, Zhongxiang Ling, Tao Jiang, Fuxiang Zhang, Pengyuan Wang, Lei Yuan, Zongzhang Zhang, and Yang Yu. Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function. In: Advances in Neural Information Processing Systems 38 (NeurIPS-2025), pages 13117-13141, San Diego, USA, 2025. [Paper] [Code]

2024

• Tao Jiang, Lei Yuan, Lihe Li, Cong Guan, Zongzhang Zhang, and Yang Yu. Multi-Agent Domain Calibration with a Handful of Offline Data. In: Advances in Neural Information Processing Systems 37 (NeurIPS-2024), pages 69607-69636, Vancouver, Canada, 2024. [Paper] [Code]
• Jiafei Lyu, Kang Xu, Jiacheng Xu, Mengbei Yan, Jing-Wen Yang, Zongzhang Zhang, Chenjia Bai, Zongqing Lu, and Xiu Li. ODRL: A Benchmark for Off-Dynamics Reinforcement Learning. In: Advances in Neural Information Processing Systems 37 (NeurIPS-2024), pages 59859-59911, Vancouver, Canada, 2024. [Paper] [Code]
• Xinyu Zhang, Wenjie Qiu, Yi-Chen Li, Lei Yuan, Chengxing Jia, Zongzhang Zhang, and Yang Yu. Debiased Offline Representation Learning for Fast Online Adaptation in Non-Stationary Dynamics. In: Proceedings of the 41st International Conference on Machine Learning (ICML-2024), pages 59741-59758, Vienna, Austria, 2024. [Paper] [Code]
• Xiong-Hui Chen, Junyin Ye, Hang Zhao, Yi-Chen Li, Xu-Hui Liu, Haoran Shi, Yu-Yan Xu, Zhihao Ye, Si-Hang Yang, Yang Yu, Anqi Huang, Kai Xu, and Zongzhang Zhang. Deep Demonstration Tracing: Learning Generalizable Imitator for Runtime One-Shot Imitation. In: Proceedings of the 41st International Conference on Machine Learning (ICML-2024), pages 7586-7620, Vienna, Austria, 2024. [Paper] [Code] [Project Page]
• Rui Kong, Chenyang Wu, Chen-Xiao Gao, Zongzhang Zhang, and Ming Li. Efficient and Stable Offline-to-Online Reinforcement Learning via Continual Policy Revitalization. In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI-2024), pages 4317-4325, Jeju Island, South Korea, 2024. [Paper] [Appendix] [Code]
• Chao Chen, Jiacheng Xu, Weijian Liao, Hao Ding, Zongzhang Zhang, Yang Yu, and Rui Zhao. Focus-Then-Decide: Segmentation-Assisted Reinforcement Learning. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-2024), pages 11240–11248, Vancouver, Canada, 2024. [Paper] [Appendix] [Code] [Project Page]
• Chen-Xiao Gao, Chenyang Wu, Mingjun Cao, Rui Kong, Zongzhang Zhang, and Yang Yu. ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-2024), pages 12127–12135, Vancouver, Canada, 2024. [Paper] [Appendix] [Code]
• Renzhe Zhou, Chen-Xiao Gao, Zongzhang Zhang, and Yang Yu. Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-2024), pages 17132-17140, Vancouver, Canada, 2024. [Paper] [Appendix] [Code]
• Yujian Zhu, Hao Ding, and Zongzhang Zhang. Multi-Expert Distillation for Few-Shot Coordination (Student Abstract). In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-2024), pages 23717-23719, Vancouver, Canada, 2024. [Paper] [Appendix] [Code]
• Rui Kong, Chenyang Wu, and Zongzhang Zhang. Generalizable Policy Improvement via Reinforcement Sampling (Student Abstract). In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-2024), pages 23546-23547, Vancouver, Canada, 2024. [Paper] [Appendix]
• Chao Chen, Dawei Wang, Feng Mao, Jiacheng Xu, Zongzhang Zhang, and Yang Yu. Deep Anomaly Detection via Active Anomaly Search. In: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2024), pages 308–316, Auckland, New Zealand, 2024. [Paper] [Appendix] [Code]
• Chengxing Jia, Fuxiang Zhang, Yi-Chen Li, Chen-Xiao Gao, Xu-Hui Liu, Lei Yuan, Zongzhang Zhang, and Yang Yu. Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation. In: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2024), pages 944–953, Auckland, New Zealand, 2024. [Paper] [Code]
• Zican Hu, Zongzhang Zhang, Huaxiong Li, Chunlin Chen, Hongyu Ding, and Zhi Wang. Attention-Guided Contrastive Role Representations for Multi-Agent Reinforcement Learning. In: Proceedings of the 12th International Conference on Learning Representations (ICLR-2024), Vienna, Austria, 2024. [Paper] [Code]
• Chengxing Jia, Chen-Xiao Gao, Hao Yin, Fuxiang Zhang, Xiong-Hui Chen, Tian Xu, Lei Yuan, Zongzhang Zhang, Yang Yu, and Zhi-Hua Zhou. Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning. In: Proceedings of the 12th International Conference on Learning Representations (ICLR-2024), Vienna, Austria, 2024. [Paper]
• Jing-Cheng Pang, Pengyuan Wang, Kaiyuan Li, Xiong-Hui Chen, Jiacheng Xu, Zongzhang Zhang, and Yang Yu. Language Model Self-Improvement by Reinforcement Learning Contemplation. In: Proceedings of the 12th International Conference on Learning Representations (ICLR-2024), Vienna, Austria, 2024. [Paper] [Code]
• Feng Chen, Fuguang Han, Cong Guan, Lei Yuan, Zhilong Zhang, Yang Yu, and Zongzhang Zhang. Stable Continual Reinforcement Learning via Diffusion-Based Trajectory Replay. In: ICLR 2024 Workshop on Generative Models for Decision Making, Vienna, Austria, 2024. [Paper]
• Lei Yuan, Tao Jiang, Lihe Li, Feng Chen, Zongzhang Zhang, and Yang Yu. Robust Cooperative Multi-Agent Reinforcement Learning via Multi-View Message Certification. SCIENCE CHINA Information Sciences, 2024, 67(4): 142102:1-142102:15. [Paper] [Code]
• Rongjun Qin, Feng Chen, Tonghan Wang, Lei Yuan, Xiaoran Wu, Yipeng Kang, Zongzhang Zhang, Chongjie Zhang, and Yang Yu. Multi-Agent Policy Transfer via Task Relationship Modeling. SCIENCE CHINA Information Sciences, 2024, 67(6): 182101:1-182101:13. [Paper] [Code]
  This work also appeared in: Deep RL Workshop on Neural Information Processing Systems, New Orleans, USA, 2022.
• Lei Yuan, Feng Chen, Zongzhang Zhang, and Yang Yu. Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation. Frontiers of Computer Science, 2024, 18(6): 186331. [Paper]
• Chengxing Jia, Fuxiang Zhang, Tian Xu, Jing-Cheng Pang, Zongzhang Zhang, and Yang Yu. Model Gradient: Unified Model and Policy Learning in Model-Based Reinforcement Learning. Frontiers of Computer Science, 2024, 18(4): 184339. [Paper]
• Cong Guan, Feng Chen, Ke Xue, Chunpeng Fan, Lichao Zhang, Ziqian Zhang, Pengyao Zhao, Zongzhang Zhang, Chao Qian, Lei Yuan, and Yang Yu. One by One, Continual Coordinating with Humans via Hyper-Teammate Identification. Transactions on Machine Learning Research, 2024, 10: 1-33. [Paper] [Code]
  This work also appeared in: ICLR 2024 Workshop on Generative Models for Decision Making, Vienna, Austria, 2024.

2023

• Chenyang Wu and Zongzhang Zhang. Surfing Information: The Challenge of Intelligent Decision-Making. Intelligent Computing, 2023, 2: Article 0041. [Paper]
• Jiacheng Xu, Chao Chen, Fuxiang Zhang, Lei Yuan, Zongzhang Zhang, and Yang Yu. Internal Logical Induction for Pixel-Symbolic Reinforcement Learning. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD-2023), pages 2825–2837, Long Beach, CA, USA, 2023. [Paper] [Code]
• Yuhang Ran, Yi-Chen Li, Fuxiang Zhang, Zongzhang Zhang, and Yang Yu. Policy Regularization with Dataset Constraint for Offline Reinforcement Learning. In: Proceedings of the 40th International Conference on Machine Learning (ICML-2023), pages 28701-28717, Honolulu, Hawaii, USA, 2023. [Paper] [Code]
• Guoqing Liu, Di Xue, Shufang Xie, Yingce Xia, Austin Tripp, Krzysztof Maziarz, Marwin Segler, Tao Qin, Zongzhang Zhang, and Tie-Yan Liu. Retrosynthetic Planning with Dual Value Networks. In: Proceedings of the 40th International Conference on Machine Learning (ICML-2023), pages 22266-22276, Honolulu, Hawaii, USA, 2023. [Paper] [Code]
• Fuxiang Zhang, Chengxing Jia, Yi-Chen Li, Lei Yuan, Yang Yu, and Zongzhang Zhang. Discovering Generalizable Multi-Agent Coordination Skills from Multi-Task Offline Data. In: Proceedings of the 11th International Conference on Learning Representations (ICLR-2023), Kigali, Rwanda, 2023. [Paper] [Code]
• Weijian Liao, Zongzhang Zhang, and Yang Yu. Policy-Independent Behavioral Metric-Based Representation for Deep Reinforcement Learning. In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-2023), pages 8746-8754, Washington, DC, USA, 2023. [Paper] [Appendix]
• Aoran Wang, Hongyang Yang, Feng Mao, Zongzhang Zhang, Yang Yu, and Xiaoyang Liu. Anti-Drifting Feature Selection via Deep Reinforcement Learning (Student Abstract). In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-2023), pages 16356-16357, Washington, DC, USA, 2023. [Paper]     (Best Student Abstract Award - Honorable Mention)
• Chao Chen, Dawei Wang, Feng Mao, Zongzhang Zhang, and Yang Yu. Deep Anomaly Detection and Search via Reinforcement Learning (Student Abstract). In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-2023), pages 16180-16181, Washington, DC, USA, 2023. [Paper]
• Feng Chen, Chenghe Wang, Fuxiang Zhang, Hao Ding, Qiaoyong Zhong, Shiliang Pu, and Zongzhang Zhang. Towards Deployment-Efficient and Collision-Free Multi-Agent Path Finding (Student Abstract). In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-2023), pages 16182-16183, Washington, DC, USA, 2023. [Paper] [Appendix]
• Fuguang Han and Zongzhang Zhang. Expert Data Augmentation in Imitation Learning (Student Abstract). In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-2023), pages 16220-16221, Washington, DC, USA, 2023. [Paper] [Appendix]
• Yi-Chen Li, Wen-Jie Shen, Boyu Zhang, Feng Mao, Zongzhang Zhang, and Yang Yu. Learning Generalizable Batch Active Learning Strategies via Deep Q-Networks (Student Abstract). In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-2023), pages 16258-16259, Washington, DC, USA, 2023. [Paper] [Appendix]
• Renzhe Zhou, Zongzhang Zhang, and Yang Yu. Model-based Offline Weighted Policy Optimization (Student Abstract). In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-2023), pages 16392-16393, Washington, DC, USA, 2023. [Paper]
• Xuhui Liu, Feng Xu, Xinyu Zhang, Tianyuan Liu, Shengyi Jiang, Ruifeng Chen, Zongzhang Zhang, and Yang Yu. How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement. In: Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2023), pages 1276-1284, London, United Kingdom, 2023. [Paper] [Appendix] [Code]

2022

• Chenyang Wu, Tianci Li, Zongzhang Zhang, and Yang Yu. Bayesian Optimistic Optimization: Optimistic Exploration for Model-Based Reinforcement Learning. In: Advances in Neural Information Processing Systems 35 (NeurIPS-2022), pages 14210-14223, New Orleans, USA, 2022. [Paper] [Appendix]
• Cong Guan, Feng Chen, Lei Yuan, Chenghe Wang, Hao Yin, Zongzhang Zhang, and Yang Yu. Efficient Multi-Agent Communication via Self-Supervised Information Aggregation. In: Advances in Neural Information Processing Systems 35 (NeurIPS-2022), pages 1020-1033, New Orleans, USA, 2022. [Paper] [Appendix] [Code] [Demo]
• Ke Xue, Jiacheng Xu, Lei Yuan, Miqing Li, Chao Qian, Zongzhang Zhang, and Yang Yu. Multi-Agent Dynamic Algorithm Configuration. In: Advances in Neural Information Processing Systems 35 (NeurIPS-2022), pages 20147-20161, New Orleans, USA, 2022. [Paper] [Appendix] [Code] [Demo]
• Di Xue, Lei Yuan, Zongzhang Zhang, and Yang Yu. Efficient Multi-Agent Communication via Shapley Message Value. In: Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI-2022), pages 578-584, Vienna, Austria, 2022. [Paper] [Code] [Demo]
• Lei Yuan, Chenghe Wang, Jianhao Wang, Fuxiang Zhang, Feng Chen, Cong Guan, Zongzhang Zhang, Chongjie Zhang, and Yang Yu. Multi-Agent Concentrative Coordination with Decentralized Task Representation. In: Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI-2022), pages 599-605, Vienna, Austria, 2022. [Paper] [Code] [Demo]
• Lei Yuan, Jianhao Wang, Fuxiang Zhang, Chenghe Wang, Zongzhang Zhang, Yang Yu, and Chongjie Zhang. Multi-Agent Incentive Communication via Decentralized Teammate Modeling. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI-2022), pages 9466-9474, Virtual Conference, 2022. [Paper] [Code] [Demo]
• Fan-Ming Luo, Shengyi Jiang, Yang Yu, Zongzhang Zhang, and Yi-Feng Zhang. Adapt to Environment Sudden Changes by Learning a Context Sensitive Policy. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI-2022), pages 7637-7646, Virtual Conference, 2022. [Paper] [Code]
• 常田, 章宗长, 俞扬. 随机集成策略迁移. 计算机科学与探索, 2022, 16(11): 2531-2536. [Paper]
• 章宗长, 俞扬. 单智能体强化学习. 分布式人工智能, 安波, 高阳, 俞扬等著, 电子工业出版社, 2022.11, 207-246.

2021

• Chenyang Wu, Guoyu Yang, Zongzhang Zhang, Yang Yu, Dong Li, Wulong Liu, and Jianye Hao. Adaptive Online Packing-Guided Search for POMDPs. In: Advances in Neural Information Processing Systems 34 (NeurIPS-2021), pages 28419-28430, Virtual Conference, 2021. [Paper] [Appendix] [Code]
• Xiong-Hui Chen, Shengyi Jiang, Feng Xu, Zongzhang Zhang, and Yang Yu. Cross-Modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning. In: Advances in Neural Information Processing Systems 34 (NeurIPS-2021), pages 12520-12532, Virtual Conference, 2021. [Paper] [Appendix] [Code]
• Yan Zheng, Jianye Hao, Zongzhang Zhang, Zhaopeng Meng, Tianpei Yang, Yanran Li, and Changjie Fan. Efficient Policy Detecting and Reusing for Non-Stationarity in Markov Games. Autonomous Agents and Multi-Agent Systems, 2021, 35(2): 1-29. [Paper]
• Feng Xu, Shengyi Jiang, Hao Yin, Zongzhang Zhang, Yang Yu, Ming Li, Dong Li, and Wulong Liu. Enhancing Context-Based Meta-Reinforcement Learning Algorithms via An Efficient Task Encoder (Student Abstract). In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI-2021), pages 15937-15938, Virtual Conference, 2021. [Paper]
• Chenyang Wu, Rui Kong, Guoyu Yang, Xianghan Kong, Zongzhang Zhang, Yang Yu, Dong Li, and Wulong Liu. LB-DESPOT: Efficient Online POMDP Planning Considering Lower Bound in Action Selection (Student Abstract). In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI-2021), pages 15927-15928, Virtual Conference, 2021. [Paper]
• 陈子璇, 章宗长, 潘致远, 张琳婧. 一种基于广义异步值迭代的规划网络模型. 软件学报, 2021, 32(11): 3496-3511. [Paper]
• 姜冲, 章宗长, 陈子璇, 朱佳成, 蒋俊鹏. 一种数据高效的第三人称模仿学习方法. 计算机科学, 2021, 48(2): 238-244. [Paper]

2020

• Cong Fei, Bing Wang, Yuzheng Zhuang, Zongzhang Zhang, Jianye Hao, Hongbo Zhang, Xuewu Ji, and Wulong Liu. Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI-2020), pages 2929-2935, Yokohama, Japan, 2020. [Paper]
  
• Tianpei Yang, Jianye Hao, Zhaopeng Meng, Zongzhang Zhang, Weixun Wang, Yujing Hu, Yingfeng Chen, Changjie Fan, Wulong Liu, Zhaodong Wang, and Jiajie Peng. Efficient Deep Reinforcement Learning via Adaptive Policy Transfer. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI-2020), pages 3094-3100, Yokohama, Japan, 2020. [Paper]
  This work also appeared in: Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2020), pages 2053-2055, as an extended abstract.
• Yan Zheng, Jianye Hao, Zongzhang Zhang, Zhaopeng Meng, and Xiaotian Hao. Efficient Multiagent Policy Optimization Based on Weighted Estimators in Stochastic Environments. Journal of Computer Science and Technology, 2020, 35(2): 268-280. [Paper]
• Chong Jiang, Zongzhang Zhang, Zixuan Chen, Jiacheng Zhu, and Junpeng Jiang. Third-Person Imitation Learning via Image Difference and Variational Discriminator Bottleneck (Student Abstract). In: Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-2020), pages 13819-13820, New York, USA, 2020. [Paper]
• Jiacheng Zhu, Jiahao Lin, Meng Wang, Yingfeng Chen, Changjie Fan, Chong Jiang, and Zongzhang Zhang. Generative Adversarial Imitation learning from Failed Experiences (Student Abstract). In: Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-2020), pages 13997-13998, New York, USA, 2020. [Paper]
• Linjing Zhang and Zongzhang Zhang. Double Replay Buffers with Restricted Gradient. In: Proceedings of the 27th International Conference on Neural Information Processing (ICONIP-2020), pages 295-306, Bangkok, Thailand, 2020. [Paper]
• Zhen Wu, Zongzhang Zhang, and Xiaofang Zhang. Recency-Weighted Acceleration for Continuous Control through Deep Reinforcement Learning. In: Proceedings of the 27th International Conference on Neural Information Processing (ICONIP-2020), pages 604-615, Bangkok, Thailand, 2020. [Paper]
• 林嘉豪, 章宗长, 姜冲, 郝建业. 基于生成对抗网络的模仿学习综述. 计算机学报, 2020, 43(2): 326-351. [Paper]

2019

• Xiaobai Ma, Katherine R. Driggs-Campbell, Zongzhang Zhang, and Mykel J. Kochenderfer. Monte-Carlo Tree Search for Policy Optimization. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-2019), pages 3116-3122, Macao, China, 2019. [Paper]
• Linjing Zhang, Zongzhang Zhang, Zhiyuan Pan, Yingfeng Chen, Jiangcheng Zhu, Zhaorong Wang, Meng Wang, and Changjie Fan. A Framework of Dual Replay Buffer: Balancing Forgetting and Generalization in Reinforcement Learning. In: Proceedings of the 2nd Workshop on Scaling Up Reinforcement Learning (SURL), International Joint Conference on Artificial Intelligence (IJCAI), Macao, China, 2019. [Paper]
• Shan Zhong, Quan Liu, Zongzhang Zhang, and Qiming Fu. Efficient Reinforcement Learning in Continuous State and Action Spaces with Dyna and Policy Approximation, Frontiers of Computer Science, 2019, 13(1): 106-126. [Paper]
• Zixuan Chen and Zongzhang Zhang. Deep Recurrent Policy Networks for Planning under Partial Observability. In: Proceedings of the 28th International Conference on Artificial Neural Networks (ICANN-2019), Part I: Theoretical Neural Computation, pages 598-610, Munich, Germany, 2019. [Paper]
• Yisheng Wang and Zongzhang Zhang. Experience Selection in Multi-Agent Deep Reinforcement Learning. In: Proceedings of the 31st International Conference on Tools with Artificial Intelligence (ICTAI-2019), pages 864-870, Portland, USA, 2019. [Paper]
• 徐进, 刘全, 章宗长, 梁斌, 周倩. 基于多重门限机制的异步深度强化学习. 计算机学报, 2019, 42(3): 636-653. [Paper]
• 陈松, 章晓芳, 章宗长, 刘全, 吴金金, 闫岩. 基于线性动态跳帧的深度双Q网络. 计算机学报, 2019, 42(11): 2561-2573. [Paper]
• 章宗长, 王艺深. 以开源项目为驱动的软件工程课程改革与研究. 计算机教育, 2019, 289(1): 84-87. [Paper]
• 刘全, 傅启明, 章宗长译. 基于函数逼近的强化学习与动态规划. 人民邮电出版社, 2019.4, 1-249.
• 章宗长, 郝建业, 俞扬. 强化学习. 数据智能研究前沿, 徐宗本, 姚新编著, 上海交通大学出版社, 2019.12, 209-278.

2018

• Yan Zheng, Zhaopeng Meng, Jianye Hao, Zongzhang Zhang, Tianpei Yang, and Changjie Fan. A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents. In: Advances in Neural Information Processing Systems 31 (NeurIPS-2018), pages 960-970, Montreal, Canada, 2018. [Paper] [Appendix]
• Zongzhang Zhang and Mykel J. Kochenderfer. Decision-Theoretic Planning in Partially Observable Environments. Interactions in Multiagent Systems, J. Hao and H. Leung Eds., World Scientific, 2018, 65-90. [Paper]
• Jiahao Lin and Zongzhang Zhang. ACGAIL: Imitation Learning about Multiple Intentions with Auxiliary Classifier GANs. In: Proceedings of the 15th Pacific Rim International Conference on Artificial Intelligence (PRICAI-2018), pages 321-334, Nanjing, China, 2018. [Paper]
• Yan Zheng, Zhaopeng Meng, Jianye Hao, and Zongzhang Zhang. Weighted Double Deep Multiagent Reinforcement Learning in Stochastic Cooperative Environments. In: Proceedings of the 15th Pacific Rim International Conference on Artificial Intelligence (PRICAI-2018), pages 421-429, Nanjing, China, 2018. [Paper]
• Zhiyuan Pan, Zongzhang Zhang, and Zixuan Chen. Asynchronous Value Iteration Network. In: Proceedings of the 25th International Conference on Neural Information Processing (ICONIP-2018), pages 169-180, Siem Reap, Cambodia, 2018. [Paper]
• Hongyao Tang, Jianye Hao, Tangjie Lv, Yingfeng Chen, Zongzhang Zhang, Hangtian Jia, Chunxu Ren, Yan Zheng, Changjie Fan, and Li Wang. Hierarchical Deep Multiagent Reinforcement Learning with Temporal Abstraction. arXiv preprint arXiv: 1809.09332v2. [Paper]
• 刘全, 翟建伟, 章宗长, 钟珊, 周倩, 章鹏, 徐进. 深度强化学习综述. 计算机学报, 2018, 41(1): 1-27. [Paper]    (2017-2021's Best Paper Award)
• 章宗长. 部分可观察环境中的序贯决策理论及方法研究. 多智能体系统及应用(卷二), 王崇骏, 史忠植, 常亮, 王文剑主编, 清华大学出版社, 2018.1, 94-111.
• 章宗长, 王艺深等译. Python数据科学导论：概念、技术与应用. 机械工业出版社, 2018.8, 1-182.

2017

• Zongzhang Zhang, Zhiyuan Pan, and Mykel J. Kochenderfer. Weighted Double Q-learning. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI-2017), pages 3455-3461, Melbourne, Australia, 2017. [Paper]
• 刘全, 翟建伟, 钟珊, 章宗长, 周倩, 章鹏. 一种基于视觉注意力机制的深度循环Q网络模型. 计算机学报, 2017, 40(6): 1353-1366. [Paper]
• 高阳, 操龙兵, 靳小龙, 史颖欢, 章宗长, 钱宇华. 数据科学中的机器学习基础和进展. CCF2016-2017中国计算机科学技术发展报告会, 2017, 116-142. [LINK]

2016

• Zongzhang Zhang, Qiming Fu, Xiaofang Zhang, and Quan Liu. Reasoning and Predicting POMDP Planning Complexity via Covering Numbers. Frontiers of Computer Science, 2016, 10(4): 726-740. [Paper]
• Zongzhang Zhang and Quan Liu. Covering Number: Analyses for Approximate Continuous-state POMDP Planning. In: Proceedings of the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2016), pages 1293-1294, Singapore, Singapore, 2016. [Paper]
• Jianwei Zhai, Quan Liu, Zongzhang Zhang, Shan Zhong, Haijun Zhu, Peng Zhang, and Cijia Sun. Deep Q-learning with Prioritized Sampling. In: Proceedings of the 23rd International Conference on Neural Information Processing (ICONIP-2016), pages 13-22, Kyoto, Japan, 2016. [Paper]     (Finalist of Best Student Paper Award)
• Weisheng Qian, Quan Liu, Zongzhang Zhang, Zhiyuan Pan, and Shan Zhong. Policy Graph Pruning and Optimization in Monte Carlo Value Iteration for Continuous-State POMDPs. In: Proceedings of the 2016 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE ADPRL-2016), Athens, Greece, 2016. [Paper]
• 章晓芳, 章宗长, 谢晓园, 周谊成. 一种基于优先级的迭代划分测试方法. 计算机学报, 2016, 39(11): 2307-2323. [Paper]

2015

• Zongzhang Zhang, David Hsu, Wee Sun Lee, Zhan Wei Lim, and Aijun Bai. PLEASE: Palm Leaf Search for POMDPs with Large Observation Spaces. In: Proceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS-2015), pages 249-257, Jerusalem. Israel, 2015. [Paper]
  This work also appeared in: Proceedings of the 8th Annual Symposium on Combinatorial Search (SoCS-2015), pages 238-239, as a two-page abstract.
• Yicheng Zhou, Quan Liu, Qiming Fu, and Zongzhang Zhang. Trajectory Sampling Value Iteration: Improved Dyna Search for MDPs. In: Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2015), pages 1685-1686, Istanbul, Turkey, 2015. [Paper]
• Shuhua You, Quan Liu, Zongzhang Zhang, Hui Wang, and Xiaofang Zhang. Intelligent Model Learning Based on Variance for Bayesian Reinforcement Learning. In: Proceedings of the 27th International IEEE Conference on Tools with Artificial Intelligence (ICTAI-2015), pages 170-177, Salerno, Italy, 2015. [Paper]
• 钟珊, 刘全, 傅启明, 章宗长, 朱斐, 龚声蓉. 一种近似模型表示的启发式Dyna优化算法. 计算机研究与发展, 2015, 52(12): 2764-2775. [Paper]

2014

• Zongzhang Zhang, David Hsu, and Wee Sun Lee. Covering Number for Efficient Heuristic-Based POMDP Planning. In: Proceedings of the 31st International Conference on Machine Learning (ICML-2014), pages 28-36, Beijing, China, 2014. [Paper] [Appendix]
• Aijun Bai, Feng Wu, Zongzhang Zhang, and Xiaoping Chen. Thompson Sampling based Monte-Carlo Planning in POMDPs. In: Proceedings of the 24th International Conference on Automated Planning and Scheduling (ICAPS-2014), pages 28-36, Portsmouth, USA, 2014. [Paper]

2013

• 章宗长, 陈小平. 杂合启发式在线POMDP规划. 软件学报, 2013, 24(7): 1589-1600. [Paper]

2012

• Zongzhang Zhang, Michael L. Littman, and Xiaoping Chen. Covering Number as a Complexity Measure for POMDP Planning and Learning. In: Proceedings of the 26th AAAI Conference on Artificial Intelligence (AAAI-2012), pages 1853-1859, Toronto, Ontario, Canada, 2012. [Paper]
• Zongzhang Zhang and Xiaoping Chen. FHHOP: A Factored Hybrid Heuristic Online Planning Algorithm for Large POMDPs. In: Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence (UAI-2012), pages 934-943, Catalina Island, United States, 2012. [Paper]
• 章宗长. 部分可观察马氏决策过程的复杂性理论及规划算法研究. 博士学位论文, 中国科学技术大学, 2012/6/5. [Paper]

2010

• Zongzhang Zhang and Xiaoping Chen. Accelerating Point-Based POMDP Algorithms via Greedy Strategies. In: Proceedings of International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR-2010), pages 545-556, Darmstadt, Germany, 2010. [Paper]