何自明，男，博士。2025年12月于西北工业大学计算机学院获得博士学位（计算机科学与技术专业），同月加入西北农林科技大学信息工程学院任教。2024年入选中国科协青年人才托举工程博士生专项计划（首批）。在 IEEE Trans. Ind. Inform., IEEE Trans. Emerg. Top. Comput. Intell., IEEE Trans. Cogn. Dev. Syst., IEEE Trans. Artif. Intell., Knowledge-Based Syst., Inf. Sci., ICRA，农业工程学报等国际权威学术期刊/会议上发表论文20篇。授权/公开国家发明专利4项，取得软件著作权6项，发表论文获中国科协优秀科技论文奖、中国精品科技期刊顶尖学术论文奖、国家自然科学基金委信息学部颁发的论坛优秀论文奖等。

强化学习、多智能体系统、机器人智能决策与控制。

[1] Ziming He, Pengyu Chen, Haobin Shi, Jingchen Li, and Kao-Shing Hwang, Robotic locomotion skill learning using unsupervised reinforcement learning with controllable latent space partition, IEEE Transactions on Industrial Informatics, 2025. (SCI, 中科院1区TOP期刊, IF=9.9, IEEE汇刊)

[2] Ziming He, Jingchen Li, Fan Wu, Haobin Shi, and Kao-Shing Hwang, DeRL: Coupling Decomposition in Action Space for Reinforcement Learning Task, IEEE Transactions on Emerging Topics in Computational Intelligence, 2024. (SCI, 中科院2区, CAAI B类期刊, IF=6.5, IEEE汇刊)

[3] Ziming He, Chao Song, Jingchen Li, and Haobin Shi, PDRL: Towards Deeper States and Further Behaviors in Unsupervised Skill Discovery by Progressive Diversity, IEEE Transactions on Cognitive and Developmental Systems, 2025. (SCI, IF=4.9, IEEE汇刊)

[4] Ziming He, Zijia Wang, Yinhong Huang, and Haobin Shi, Graph-Based Communication Optimization for Multi-Agent Reinforcement Learning in Unmanned Warehousing, Journal of Communications and Information Networks, 2025. (EI, 中国科协高质量T1级期刊)

[5] Haobin Shi#, Ziming He#, Kao-Shing Hwang, A Segmented Motion Synthesis Method for Robotic Task-Oriented Locomotion Imitation System, Knowledge-Based Systems, 2025 (SCI，中科院1区TOP期刊，IF=7.6)

[6] Haobin Shi#, Ziming He#, Kao-Shing Hwang, Adaptive path planning for wafer second probing via an attention-based hierarchical reinforcement learning framework with shared memory, Information Sciences, 2025. (SCI, 中科院2区, IF=6.8)

[7] Haobin Shi#, Ziming He#, Kao-Shing Hwang, Domain adaptation with temporal ensembling to local attention region search for object detection, Knowledge-Based Systems, 2025. (SCI, 中科院1区TOP期刊，IF=7.6)

[8] Yanbin Li, Ziming He, Xingjian Gu, Huanliang Xu, Shougang Ren, AFedAvg: communication-efficient federated learning aggregation with adaptive communication frequency and gradient sparse，Journal of Experimental & Theoretical Artificial Intelligence, 2022. (SCI，CCF-C期刊)

[9] 任守纲，何自明，周正己，顾兴健，徐焕良，基于CSBFT区块链的农作物全产业链信息溯源平台设计, 农业工程学报，2020. (中文核心，EI，中国科协高质量T1级期刊，科协优秀论文，入选F5000)

[10] Shike Yang, Ziming He, Jingchen Li, Haobin Shi, Kao-Shing Hwang, et al., Neighborhood curiosity-based exploration in multi-agent reinforcement learning, IEEE Transactions on Cognitive and Developmental Systems, 2024（SCI, IF=4.9, IEEE汇刊）

[11] Quantao Wang, Ziming He, Haobin Shi, Simplifying communication control: a cooperative multi-agent reinforcement learning framework based on group decision-making, Journal of King Saud University Computer and Information Sciences, 2025（SCI, IF=6.1, 中科院2区）

[12] Jingchen Li, Yusen Yang, Ziming He, Huarui Wu, Chunjiang Zhao, et al, Investigating Primacy Bias in Multi-Agent Reinforcement Learning: An Empirical Study, IEEE Transactions on Artificial Intelligence, 2025（SCI, CiteScore=7.7, IEEE汇刊）

[13] Zehan Wang, Ziming He, Zijia Wang, Hua He, Beiya Yang, et al, MJPR: Multi-modal Joint Predictive Representation in Deep Reinforcement Learning, IEEE International Conference on Robotics and Automation (ICRA 2025),（机器人领域TOP会议）

[14] Jingchen Li, Yusen Yang, Ziming He, Huarui Wu, Haobin Shi, Wenbai Chen, Cournot policy model: Rethinking centralized training in multi-agent reinforcement learning, Information Sciences, 2024（SCI，中科院2区，IF=6.8）

[15] Yang Liu, Ying Zhou, Ziming He, Yusen Yang, Qingcen Han, Jingchen Li, Dynamic preference inference network: Improving sample efficiency for multi-objective reinforcement learning by preference estimation, Knowledge-Based Systems, 2024（SCI，中科院1区TOP期刊，IF=7.6）

[1] 中国科学技术协会，中国科协青年人才托举工程博士生专项计划项目，2025-01至2025-12，主持

[2] 西北农林科技大学，博士科研启动经费项目，2026-01至2029-01，主持

[3] 国家自然科学基金委员会，重大研究计划（培育）项目，面向无人工厂的多智能体协同与决策机制，2023-01至2025-12，参与

[4] 国家自然科学基金委员会，面上项目，复杂环境下移动机器人自主导航及控制方法研究， 2021-01至2024-12，参与

[5] 之江实验室，重点实验室开放课题，基于强化学习的双足机器人多运动模式与抗扰控制方法研究，2022-02至2024-01，参与