{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:34:31Z","timestamp":1771025671214,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T00:00:00Z","timestamp":1706227200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,26]]},"DOI":"10.1145\/3640824.3640843","type":"proceedings-article","created":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T12:05:28Z","timestamp":1709899528000},"page":"120-127","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Robot Cooperative Pursuit-Evasion Control: A DeepReinforcement Learning Approach based on Prioritized Experience Replay"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1074-3241","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Henan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4407-7856","authenticated-orcid":false,"given":"Wenhao","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Henan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5984-4588","authenticated-orcid":false,"given":"Huaguang","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence,, Henan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5350-7283","authenticated-orcid":false,"given":"Si","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Henan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7657-6100","authenticated-orcid":false,"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Henan University, China"}]}],"member":"320","published-online":{"date-parts":[[2024,3,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics. ArXiv abs\/1910.01465","author":"Ackermann J.H.","year":"2019","unstructured":"Johann\u00a0J.H. Ackermann, Volker Gabler, Takayuki Osa, and Masashi Sugiyama. 2019. Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics. ArXiv abs\/1910.01465 (2019). https:\/\/api.semanticscholar.org\/CorpusID:203642167"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068952"},{"key":"e_1_3_2_1_3_1","volume-title":"Multi-Agent Distributed Deep Deterministic Policy Gradient for Partially Observable Tracking. Actuators","author":"Fan Dongyu","year":"2021","unstructured":"Dongyu Fan, Haikuo Shen, and Lijing Dong. 2021. Multi-Agent Distributed Deep Deterministic Policy Gradient for Partially Observable Tracking. Actuators (2021). https:\/\/api.semanticscholar.org\/CorpusID:244581930"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2958548"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40840-019-00844-3"},{"key":"e_1_3_2_1_6_1","volume-title":"Addressing Function Approximation Error in Actor-Critic Methods. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:3544558","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke van Hoof, and David Meger. 2018. Addressing Function Approximation Error in Actor-Critic Methods. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:3544558"},{"key":"e_1_3_2_1_7_1","volume-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. ArXiv abs\/1801.01290","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, P. Abbeel, and Sergey Levine. 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. ArXiv abs\/1801.01290 (2018). https:\/\/api.semanticscholar.org\/CorpusID:28202810"},{"key":"e_1_3_2_1_8_1","volume-title":"Distributed Prioritized Experience Replay. ArXiv abs\/1803.00933","author":"Horgan Dan","year":"2018","unstructured":"Dan Horgan, John Quan, David Budden, Gabriel Barth-Maron, Matteo Hessel, H.\u00a0V. Hasselt, and David Silver. 2018. Distributed Prioritized Experience Replay. ArXiv abs\/1803.00933 (2018). https:\/\/api.semanticscholar.org\/CorpusID:3463260"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114896"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015960"},{"key":"e_1_3_2_1_11_1","volume-title":"Branching Improved Deep Q Networks for Solving Pursuit-Evasion Strategy Solution of Spacecraft.Journal of Industrial & Management Optimization 18, 2","author":"Liu Bingyan","year":"2022","unstructured":"Bingyan Liu, Xiongbing Ye, Xianzhou Dong, and Lei Ni. 2022. Branching Improved Deep Q Networks for Solving Pursuit-Evasion Strategy Solution of Spacecraft.Journal of Industrial & Management Optimization 18, 2 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3522749.3523066"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2926554"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3136286"},{"key":"e_1_3_2_1_15_1","volume-title":"Multi-Agent Cooperative Pursuit-Evasion Control Using Gene Expression Programming. IECON 2021 \u2013 47th Annual Conference of the IEEE Industrial Electronics Society","author":"Ni Yinjie","year":"2021","unstructured":"Yinjie Ni, Shuhua Gao, Sunan Huang, Cheng Xiang, Qinyuan Ren, and Tong heng Lee. 2021. Multi-Agent Cooperative Pursuit-Evasion Control Using Gene Expression Programming. IECON 2021 \u2013 47th Annual Conference of the IEEE Industrial Electronics Society (2021), 1\u20136. https:\/\/api.semanticscholar.org\/CorpusID:243946532"},{"key":"e_1_3_2_1_16_1","volume-title":"Co-Evolution of Predator-Prey Ecosystems by Reinforcement Learning Agents. Entropy 23","author":"Park Jeongho","year":"2021","unstructured":"Jeongho Park, Juwon Lee, Taehwan Kim, Inkyung Ahn, and Jooyoung Park. 2021. Co-Evolution of Predator-Prey Ecosystems by Reinforcement Learning Agents. Entropy 23 (2021). https:\/\/api.semanticscholar.org\/CorpusID:233396873"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-018-2591-3"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974695"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188904"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912200"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3230983"},{"key":"e_1_3_2_1_22_1","volume-title":"MADDPG: An Efficient Multi-Agent Reinforcement Learning Algorithm. In Other Conferences. https:\/\/api.semanticscholar.org\/CorpusID:249720545","author":"Song Xinyu","year":"2022","unstructured":"Xinyu Song. 2022. MADDPG: An Efficient Multi-Agent Reinforcement Learning Algorithm. In Other Conferences. https:\/\/api.semanticscholar.org\/CorpusID:249720545"},{"key":"e_1_3_2_1_23_1","volume-title":"Xiao guang Gao, and Zijian Hu","author":"Wan Kaifang","year":"2021","unstructured":"Kaifang Wan, Dingwei Wu, Yiwei Zhai, Bo Li, Xiao guang Gao, and Zijian Hu. 2021. An Improved Approach towards Multi-Agent Pursuit\u2013Evasion Game Decision-Making Using Deep Reinforcement Learning. Entropy 23 (2021). https:\/\/api.semanticscholar.org\/CorpusID:242056317"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCRE55123.2022.9770236"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3068259"},{"key":"e_1_3_2_1_26_1","volume-title":"Research on Multi-Robot Formation Control Based on MATD3 Algorithm. Applied Sciences","author":"Zhou Conghang","year":"2023","unstructured":"Conghang Zhou, Jianxing Li, Yujing Shi, and Zhirui Lin. 2023. Research on Multi-Robot Formation Control Based on MATD3 Algorithm. Applied Sciences (2023). https:\/\/api.semanticscholar.org\/CorpusID:256530787"},{"key":"e_1_3_2_1_27_1","volume-title":"Multirobot Collaborative Pursuit Target Robot by Improved MADDPG. Computational Intelligence and Neuroscience 2022","author":"Zhou Xiaofeng","year":"2022","unstructured":"Xiaofeng Zhou, Song Zhou, Xingang Mou, and Yi He. 2022. Multirobot Collaborative Pursuit Target Robot by Improved MADDPG. Computational Intelligence and Neuroscience 2022 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247139444"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-020-01188-y"}],"event":{"name":"CCEAI 2024: 2024 8th International Conference on Control Engineering and Artificial Intelligence","location":"Shanghai China","acronym":"CCEAI 2024"},"container-title":["2024 8th International Conference on Control Engineering and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640824.3640843","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640824.3640843","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T16:45:38Z","timestamp":1756485938000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640824.3640843"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,26]]},"references-count":28,"alternative-id":["10.1145\/3640824.3640843","10.1145\/3640824"],"URL":"https:\/\/doi.org\/10.1145\/3640824.3640843","relation":{},"subject":[],"published":{"date-parts":[[2024,1,26]]},"assertion":[{"value":"2024-03-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}