{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:18:26Z","timestamp":1779293906955,"version":"3.51.4"},"publisher-location":"Cham","reference-count":10,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031779534","type":"print"},{"value":"9783031779541","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-77954-1_7","type":"book-chapter","created":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T04:34:54Z","timestamp":1732854894000},"page":"107-115","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Application and Optimization of Multi-agent Reinforcement Learning in Collaborative Decision-Making"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8395-4001","authenticated-orcid":false,"given":"Qi","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5864-7934","authenticated-orcid":false,"given":"Zhihao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0645-6455","authenticated-orcid":false,"given":"Han","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,29]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","first-page":"13677","DOI":"10.1007\/s10489-022-04105-y","volume":"53","author":"A Oroojlooy","year":"2023","unstructured":"Oroojlooy, A., Hajinezhad, D.: A review of cooperative multi-agent deep reinforcement learning. Appl. Intell. 53, 13677\u201313722 (2023)","journal-title":"Appl. Intell."},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Seitz, M., Gehlhoff, F., Cruz Salazar, L.A., et al.: Automation platform independent multi-agent system for robust networks of production resources in industry 4.0. J. Intell. Manufact. 32(7), 2023\u20132041 (2021)","DOI":"10.1007\/s10845-021-01759-2"},{"issue":"1","key":"7_CR3","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1080\/22348972.2017.1348890","volume":"7","author":"J Xie","year":"2017","unstructured":"Xie, J., Liu, C.C.: Multi-agent systems and their applications. J. Int. Coun. Elec. Eng. 7(1), 188\u2013197 (2017)","journal-title":"J. Int. Coun. Elec. Eng."},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Luo, A., Ma, H., Ren, H., et al.: Estimator-based reinforcement learning consensus control for multiagent systems with discontinuous constraints. IEEE Trans. Neural Netw. Learn. Syst. (2024)","DOI":"10.1109\/TNNLS.2024.3445880"},{"key":"7_CR5","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2023.02.009","volume":"94","author":"S Yang","year":"2023","unstructured":"Yang, S., Yang, B., Zeng, Z., et al.: Causal inference multi-agent reinforcement learning for traffic signal control. Inf. Fus. 94, 243\u2013256 (2023)","journal-title":"Inf. Fus."},{"key":"7_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102945","volume":"156","author":"Y Zhu","year":"2024","unstructured":"Zhu, Y., Xiao, M., Robbins, D., et al.: Walking representation and simulation based on multi-source image fusion and multi-agent reinforcement learning for gait rehabilitation. Artif. Intell. Med. 156, 102945 (2024)","journal-title":"Artif. Intell. Med."},{"key":"7_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2024.110987","volume":"237","author":"Q Yuan","year":"2024","unstructured":"Yuan, Q.: Residential demand response online optimization based on multi-agent deep reinforcement learning. Elec. Power Syst. Res. 237, 110987 (2024)","journal-title":"Elec. Power Syst. Res."},{"key":"7_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125116","volume":"257","author":"S Dong","year":"2024","unstructured":"Dong, S., Li, C., Yang, S., et al.: Decentralized counterfactual value with threat detection for multi-agent reinforcement learning in mixed cooperative and competitive environments. Expert Syst. Appl. 257, 125116 (2024)","journal-title":"Expert Syst. Appl."},{"key":"7_CR9","volume-title":"State Increment Dynamic Programming","author":"RE Larson","year":"1968","unstructured":"Larson, R.E.: State Increment Dynamic Programming. Elsevier, New York (1968)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Xu, B., Luan, W., Yang, J., et al.: Integrated three-stage decentralized scheduling for virtual power plants: a model-assisted multi-agent reinforcement learning method. Appl. Ener. 376(PA), 123985 (2024)","DOI":"10.1016\/j.apenergy.2024.123985"}],"container-title":["Lecture Notes in Computer Science","Cognitive Computing - ICCC 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77954-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T05:14:43Z","timestamp":1732857283000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77954-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,29]]},"ISBN":["9783031779534","9783031779541"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77954-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,29]]},"assertion":[{"value":"29 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Cognitive Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.servicessociety.org\/iccc","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}