基本信息

尹奇跃  男    中国科学院自动化研究所
电子邮件: qyyin@nlpr.ia.ac.cn
通信地址: 中国科学院自动化研究所智能化大厦406
邮政编码: 100190

研究领域

博弈决策、大语言模型智能体、机器学习、数据挖掘

招生信息

少量硕士名额;少量优秀在职硕士名额;此外,长期招聘实习生,从事自然语言嵌入的强化学习、多智能体强化学习、大语言模型智能体、多模态学习等研究。

招生专业
081104-模式识别与智能系统
招生方向
人工智能理论与方法

教育背景

2012-09--2017-07   中国科学院自动化研究所   博士学位
2008-09--2012-07   哈尔滨工程大学   学士学位

工作经历

2020-01~现在, 中国科学院自动化研究所, 副研究员
2017-07~2019-12,中国科学院自动化研究所, 助理研究员

专利与奖励

   
部分专利

[1] 尹奇跃, 黄凯奇, 赵美静. 人机对抗分布式训练系统和方法. CN202110489058.7, 2021-05-06.

[2] 尹奇跃, 黄凯奇, 赵美静. 人机对抗智能体策略制定方法. CN: CN112926729A, 2021-06-08.

[3] 黄凯奇, 尹奇跃, 张俊格, 徐沛. 基于深度强化学习网络构建对区域敏感的模型的方法. CN: CN114004370A, 2022-02-01.

[4] 黄凯奇, 赵美静, 尹奇跃. 一种人机对抗能力评估评测方法和系统. CN: CN113902355A, 2022-01-07.

部分奖励

(1)中国指挥与控制学会科学技术进步奖一等奖,2023

(2)中国图象图形学报高关注度领域综述,2023

(3)IJCAI-Neural MMO挑战赛银奖,2022

(4)AIIDE星际争霸AI全球挑战赛第三名, 2018

(5)CCF-滴滴盖亚青年学者科研基金, 2018

(6)AIIDE星际争霸AI全球挑战赛第四名, 2017

出版信息

部分期刊论文

  • ​Qiyue Yin, Tongtong Yu, Shengqi Shen et al.. Distributed deep reinforcement learning: A survey and a multi-player multi-agent learning toolbox. MIR, 2024, 21(3): 411-430.
  • ​Qiyue Yin, Jun Yang, Kaiqi Huang, et al.. AI in human-computer gaming: Techniques, challenges and opportunities. MIR, 2023, 20(3): 299-317.
  • Yuxiang Mai, Yifan Zang, Qiyue Yin, Wancheng Ni, Kaiqi Huang. Deep multitask multiagent reinforcement learning with knowledge transfer. IEEE ToG, 2023.
  • Xiaojie Zhou, Xueou Feng, Qingming Li, Qiyue Yin, Jun Yang, Guoxia Yu, Qing Shi. Position weighted convolutional neural network for unbalanced children caries diagnosis. IEEE Access, 2023, 11: 77034-77044.
  • Peng Xu, Timothy M. Hospedales, Qiyue Yin, Yi-Zhe Song, Tao Xiang, Liang Wang. Deep Learning for Free-Hand Sketch: A Survey and A Toolbox. IEEE TPAMI, 2023, 35(1): 285-312.

  • Pei Xu, Qiyue Yin, Junge Zhang, Kaiqi Huang. Deep reinforcement learning with part-aware exploration bonus in video games. IEEE ToG, 2022, 14(4): 644-653.

  • Xiaomeng Si, Qiyue Yin, Xiaojie Zhao, Li Yao. Consistent and diverse multi-View subspace clustering with structure constraint. PR, 2022, 121: 108196.

  • Xiaomeng Si, Qiyue Yin, Xiaojie Zhao, Li Yao. Robust deep multi-view subspace clustering networks with a correntropy-induced metric. Applied Intelligence, 2022, 52(13): 14871-14877.

  • Xingzhou Lou, Qiyue Yin, Junge Zhang, et al.. Offline reinforcement learning with representations for actions. Information Sciences, 2022, 610: 746-758.

  • Peng Xu, Zeyu Song, Qiyue Yin, Yizhe Song, Liang Wang, Deep self-supervised representation learning for free-hand sketch. IEEE TCSVT, 2021, 31(4): 1503-1513.

  • Wenzhen Huang, Qiyue Yin, Junge Zhang, Kaiqi Huang. Learning macromanagement in starcraft by deep reinforcement learning. Sensors, 2021, 21(10): 3332.

  • Qiyue Yin, Junge Zhang, Shu Wu, Hexi Li, Multi-view clustering via joint feature selection and partially constrained cluster label learning. PR, 2019 (93): 380-391.

  • Qiyue Yin, Shu Wu, Liang Wang, Multiview clustering via unified and view-specific embeddings learning. IEEE TNNLS, 2018, 29(11): 5541-5553.

  • Peng Xu, Qiyue Yin, et al., Cross-modal subspace learning for fine-grained sketch-based image retrieval. Neurocomputing, 2018 (278): 75-86.

  • Qiyue Yin, Shu Wu, Liang Wang, Unified subspace learning for incomplete and unlabeled multi-view data. PR, 2017 (67): 313-327.

  • Qiyue Yin, Shu Wu, Ran He, Liang Wang, Multi-view clustering via pairwise sparse subspace representation. Neurocomputing, 2015 (156): 12-21.

  • Ran He, Yingya Zhang, Zhenan Sun, Qiyue Yin, Robust subspace clustering with complex noise. IEEE TIP, 2015, 24(11): 4001-4013.

  • Ran He, Man Zhang, Liang Wang, Ye Ji, Qiyue Yin, Cross-modal subspace learning via pairwise constraints. IEEE TIP, 2015, 24(12): 5543-5556.

  • 尹奇跃, 赵美静, 倪晚成, 张俊格, 黄凯奇. 兵棋推演的智能决策技术与挑战. 自动化学报, 2023, 49(5): 913-928.

  • 黄文振, 尹奇跃, 张俊格, 黄凯奇. 基于模型的强化学习中可学习的样本加权机制. 软件学报, 2023, 34(06): 2765-2775.

  • 周雷, 尹奇跃, 黄凯奇. 人机对抗中的博弈学习方法, 计算机学报, 2022, 45(9): 1859-1876.

  • 尹奇跃, 黄岩, 张俊格, 吴书, 王亮. 基于深度学习的跨模态检索综述. 中国图象图形学报, 2021, 26(6): 1368-1388.

部分会议论文

  • Tongtong Yu, Chenghua He, Qiyue Yin. M2RL: A Multi-player Multi-agent Reinforcement Learning Framework for Complex Games. IJCAI, 2024.
  • Yang Yu, Qiyue Yin, Junge Zhang, Pei Xu, Kaiqi Huang. ADMN: Agent-driven modular network for dynamic parameter sharing in cooperative multi-agent reinforcement learning. IJCAI, 2024.
  • Yang Yu, Qiyue Yin, Junge Zhang, Kaiqi Huang. Prioritized tasks mining for multi-task cooperative multi-agent reinforcement learning. AAMAS, 2023.
  • Pei Xu, Junge Zhang, Qiyue Yin, Chao Yu, Yaodong, Kaiqi Huang. Subspace-aware exploration for sparse-reward multi-agent tasks. AAAI, 2023.

  • Yang Yu, Qiyue Yin, Junge Zhang, Kaiqi Huang. Underexplored subspace mining for sparse-reward cooperative multi-agent reinforcement learning. IJCNN, 2023.

  • Yifei Chen, Zhourui Guo, Qiyue Yin, Hao Chen, Kaiqi Huang. Layer-wisely supervised learning for one-shot neural architecture search. IJCNN, 2022.

  • Wenzhen Huang, Qiyue Yin, Junge Zhang, Kaiqi Huang, Learning to reweight imaginary transitions for model-­based reinforcement learning. AAAI, 2021.

  • Wei Cheng, Ziyan Luo, Qiyue Yin, Adaptive prior‐dependent correction enhanced reinforcement learning for natural language generation. AAAI, 2021.

  • Peng Xu, Qiyue Yin, Yonggang Qi, Yi-Zhe Song, Zhanyu Ma, Liang Wang, Jun Guo, Instance-level coupled subspace learning for fine-grained sketch-based image retrieval. ECCV Workshops, pp. 19-34, 2016.

  • Qiyue Yin, Shu Wu, Liang Wang, Incomplete multi-view clustering via subspace learning, ACM CIKM, pp. 383-392, 2015.

  • Dong Wang, Qiyue Yin, Ran He, Liang Wang, Tieniu Tan, Multi-view clustering via structured low-rank representation, ACM CIKM, pp. 1911-1914, 2015.

  • Qiyue Yin, Shu Wu, Liang Wang, Learning to Hash for Recommendation with Tensor Data, APWeb, pp. 292-303, 2015.

  • Qiyue Yin, Shu Wu, Liang Wang, Partially tagged image clustering, ICIP, pp. 4012-4016, 2015.

科研项目

  • 策略自BY系统与提升算法研究,主持,企业委托,2024.3-2024.12.

  • 面向无人机集群对抗的多智能体自主学习研究,主持,企业委托,2024.1-2025.11

  • 训练异构资源调度软件框架设计,主持,企业委托,2022.10-2024.12

  • 新疆生产建设兵团项目实施,主持,境内委托项目,2023.9-2026.12

  • 不完全信息下多智能体高效探索与协作算法及验证系统开发,主持,企业委托,2021.3-2021.12.

  • c*智能博弈决策AI训练学习及推理平台,参与,国家任务,2020.11-2022.6.

  • **算法包子课题,主持,国家重点研发计划,2019.7-2022.7.

  • 2035人机对抗, 子课题负责人, 研究所任务, 2019-10--2021-12.

  • 小样本学习与可解释性建模,参与,中科院战略性先导科技专项A,2020.11-2024.11.

合作情况

清华大学,多智能体自适应协同与通信对抗系统研发

华为,自动化学习算子设计与加速算法研究

指导学生

   
指导

郭洲蕊,硕士研究生

陈咨列,硕士研究生

李庆明,硕士研究生

贺成华,硕士研究生

桂杨海,硕士研究生

协助指导

徐沛,博士研究生 

于杨,博士研究生 

 黄文振,博士研究生 

 程维,硕士研究生 

 陈皓,硕士研究生