{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:10:02Z","timestamp":1755861002431,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T00:00:00Z","timestamp":1700784000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,24]]},"DOI":"10.1145\/3653081.3653082","type":"proceedings-article","created":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T00:13:02Z","timestamp":1714781582000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on the application of multi-intelligence collaborative method based on imitation learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5938-2106","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"first","affiliation":[{"name":"The 15th Research Institute of China Electronics Technology Group Corporation, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8729-3971","authenticated-orcid":false,"given":"Haiyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"The 15th Research Institute of China Electronics Technology Group Corporation, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7693-0896","authenticated-orcid":false,"given":"Zhenyu","family":"Li","sequence":"additional","affiliation":[{"name":"The 15th Research Institute of China Electronics Technology Group Corporation, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0880-1816","authenticated-orcid":false,"given":"Wenshi","family":"Wang","sequence":"additional","affiliation":[{"name":"The 15th Research Institute of China Electronics Technology Group Corporation, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1455-3824","authenticated-orcid":false,"given":"Yucai","family":"Dong","sequence":"additional","affiliation":[{"name":"The 15th Research Institute of China Electronics Technology Group Corporation, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Reinforcement learning: an introduction[M]","author":"SUTTON R S","year":"2018","unstructured":"SUTTON R S, BARTO A G. Reinforcement learning: an introduction[M]. Second edition. Cambridge, Massachusetts: The MIT Press, 2018."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12525"},{"key":"e_1_3_2_1_3_1","volume-title":"\u201cOther-Play","author":"HU H","year":"2003","unstructured":"HU H, LERER A, PEYSAKHOVICH A, et.. \u201cOther-Play\u201d for Zero-Shot Coordination[J\/OL]. arXiv:2003.02979 [cs], 2021[2022-01-24]. http:\/\/arxiv.org\/abs\/2003.02979."},{"key":"e_1_3_2_1_4_1","volume-title":"et.. Diversity-driven extensible hierarchical reinforcement learning [C]\/\/Proceedings of the AAAI conference on artificial intelligence","author":"SONG Y","year":"2019","unstructured":"SONG Y, WANG J, LUKASIEWICZ T, et.. Diversity-driven extensible hierarchical reinforcement learning [C]\/\/Proceedings of the AAAI conference on artificial intelligence: volume 33. 2019: 4992-4999."},{"key":"e_1_3_2_1_5_1","volume-title":"An Overview of Multi-Agent Reinforcement Learning from Game Theoretical Perspective [J\/OL]. arXiv:2011.00583 [cs]","author":"YANG Y","year":"2021","unstructured":"YANG Y, WANG J. An Overview of Multi-Agent Reinforcement Learning from Game Theoretical Perspective [J\/OL]. arXiv:2011.00583 [cs], 2021 [2022-01-25]. http:\/\/arxiv.org\/abs\/2011.00583."},{"key":"e_1_3_2_1_6_1","volume-title":"Investigating partner diversification methods in cooperative multi-agent deep reinforcement learning[C]\/\/International Conference on Neural Information Processing","author":"CHARAKORN R","year":"2020","unstructured":"CHARAKORN R, MANOONPONG P, DILOKTHANAKUL N. Investigating partner diversification methods in cooperative multi-agent deep reinforcement learning[C]\/\/International Conference on Neural Information Processing. Springer, 2020: 395-402."},{"volume-title":"Theory and methods of autonomy for human-computer hybrid intelligent systems [M]","year":"2021","key":"e_1_3_2_1_7_1","unstructured":"Zhao Yunbo, Kang Yu, Zhu Jin. Theory and methods of autonomy for human-computer hybrid intelligent systems [M]. Science Press, 2021."},{"key":"e_1_3_2_1_8_1","volume-title":"et.. On the Importance of Environments in Human-Robot Coordination [J\/OL]. arXiv:2106.10853 [cs]","author":"FONTAINE M C","year":"2021","unstructured":"FONTAINE M C, HSU Y C, ZHANG Y, et.. On the Importance of Environments in Human-Robot Coordination [J\/OL]. arXiv:2106.10853 [cs], 2021[2022-02-04]. http:\/\/arxiv.org\/abs\/2106.10853."},{"key":"e_1_3_2_1_9_1","volume-title":"et.. Evaluating the Robustness of Collaborative Agents[J\/OL]. arXiv:2101.05507 [cs]","author":"KNOTT P","year":"2021","unstructured":"KNOTT P, CARROLL M, DEVLIN S, et.. Evaluating the Robustness of Collaborative Agents[J\/OL]. arXiv:2101.05507 [cs], 2021[2022-01-21]. http:\/\/arxiv.org\/abs\/2101.05507."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"e_1_3_2_1_11_1","volume-title":"Hierarchical reinforcement learning with the MAXQ value function decomposition[J]. Journal of artificial intelligence research","author":"DIETTERICH T G","year":"2000","unstructured":"DIETTERICH T G. Hierarchical reinforcement learning with the MAXQ value function decomposition[J]. Journal of artificial intelligence research, 2000, 13: 227-303."},{"key":"e_1_3_2_1_12_1","volume-title":"et.. On the Utility of Learning about Humans for Human-AI Coordination[C\/OL]\/\/Advances in Neural Information Processing Systems","author":"CARROLL M","year":"2019","unstructured":"CARROLL M, SHAH R, HO M K, et.. On the Utility of Learning about Humans for Human-AI Coordination[C\/OL]\/\/Advances in Neural Information Processing Systems: volume 32. Curran Associates, Inc., 2019[2022-01-25]. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/f5b1b89d98b7286673128a5fb112cb9a-Abstract.html."},{"key":"e_1_3_2_1_13_1","volume-title":"et.. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments[J\/OL]. arXiv:1706.02275 [cs]","author":"LOWE R","year":"2020","unstructured":"LOWE R, WU Y, TAMAR A, et.. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments[J\/OL]. arXiv:1706.02275 [cs], 2020[2022-02-18]. http:\/\/arxiv.org\/abs\/1706.02275."},{"key":"e_1_3_2_1_14_1","volume-title":"et.. Learning and Transfer of Modulated Locomotor Controllers[J\/OL]. arXiv:1610.05182 [cs]","author":"HEESS N","year":"2016","unstructured":"HEESS N, WAYNE G, TASSA Y, et.. Learning and Transfer of Modulated Locomotor Controllers[J\/OL]. arXiv:1610.05182 [cs], 2016[2022-02-19]. http:\/\/arxiv.org\/abs\/1610.05182."},{"key":"e_1_3_2_1_15_1","volume-title":"et.. Option discovery in hierarchical reinforcement learning using spatio-temporal clustering[J]. arXiv preprint arXiv:1605.05359","author":"SRINIVAS A","year":"2016","unstructured":"SRINIVAS A, KRISHNAMURTHY R, KUMAR P, et.. Option discovery in hierarchical reinforcement learning using spatio-temporal clustering[J]. arXiv preprint arXiv:1605.05359, 2016."},{"key":"e_1_3_2_1_16_1","volume-title":"et.. Maximum Entropy Population Based Training for Zero-Shot Human-AI Coordination[J\/OL]. arXiv:2112.11701 [cs]","author":"ZHAO R","year":"2021","unstructured":"ZHAO R, SONG J, HAIFENG H, et.. Maximum Entropy Population Based Training for Zero-Shot Human-AI Coordination[J\/OL]. arXiv:2112.11701 [cs], 2021[2022-02-04]. http:\/\/arxiv.org\/abs\/2112.11701."},{"key":"e_1_3_2_1_17_1","volume-title":"et.. PantheonRL: A MARL Library for Dynamic Training Interactions[J\/OL]. arXiv:2112.07013 [cs]","author":"SARKAR B","year":"2021","unstructured":"SARKAR B, TALATI A, SHIH A, et.. PantheonRL: A MARL Library for Dynamic Training Interactions[J\/OL]. arXiv:2112.07013 [cs], 2021[2022-02-04]. http:\/\/arxiv.org\/abs\/2112.07013."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015353"}],"event":{"name":"IoTAAI 2023: 2023 5th International Conference on Internet of Things, Automation and Artificial Intelligence","acronym":"IoTAAI 2023","location":"Nanchang China"},"container-title":["Proceedings of the 2023 5th International Conference on Internet of Things, Automation and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3653081.3653082","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3653081.3653082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T10:53:18Z","timestamp":1755859998000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3653081.3653082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,24]]},"references-count":18,"alternative-id":["10.1145\/3653081.3653082","10.1145\/3653081"],"URL":"https:\/\/doi.org\/10.1145\/3653081.3653082","relation":{},"subject":[],"published":{"date-parts":[[2023,11,24]]},"assertion":[{"value":"2024-05-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}