{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:12:43Z","timestamp":1743009163518,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811961342"},{"type":"electronic","value":"9789811961359"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-981-19-6135-9_33","type":"book-chapter","created":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T14:04:46Z","timestamp":1666274686000},"page":"442-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Improved Weighted QMIX Based on Weight Function with Q-Value"],"prefix":"10.1007","author":[{"given":"Tianyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,21]]},"reference":[{"key":"33_CR1","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"issue":"3","key":"33_CR2","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nature, 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"33_CR4","unstructured":"Yang, Y., Wang, J.: An overview of multi-agent reinforcement learning from game theoretical perspective. arXiv preprint arXiv:2011.00583 (2020)"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative agents. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 330\u2013337 (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"issue":"4","key":"33_CR6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"A Tampuu","year":"2017","unstructured":"Tampuu, A., Matiisen, T., Kodelja, D., et al.: Multiagent cooperation and competition with deep reinforcement learning. PLoS ONE 12(4), e0172395 (2017)","journal-title":"PLoS ONE"},{"key":"33_CR7","doi-asserted-by":"publisher","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: Sukthankar, G., Rodriguez-Aguilar, J. (eds.) AAMAS 2017. LNCS, vol. 10642, pp. 66\u201383. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-71682-4_5","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"33_CR8","unstructured":"Schulman, J., Levine, S., Abbeel, P., et al.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"33_CR9","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"33_CR10","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv preprint arXiv:1409.2329 (2014)"},{"key":"33_CR11","unstructured":"Sunehag, P., Lever, G., Gruslys, A., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"33_CR12","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., et al.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304. PMLR (2018)"},{"key":"33_CR13","unstructured":"Son, K., Kim, D., Kang, W.J., et al.: QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"33_CR14","first-page":"10199","volume":"33","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Farquhar, G., Peng, B., et al.: Weighted QMIX: expanding monotonic value function factorisation for deep multi-agent reinforcement learning. Adv. Neural Inf. Process. Syst. 33, 10199\u201310210 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"33_CR15","unstructured":"Samvelyan, M., Rashid, T., De Witt, C.S., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)"}],"container-title":["Communications in Computer and Information Science","Neural Computing for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-6135-9_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T14:10:06Z","timestamp":1666275006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-6135-9_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811961342","9789811961359"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-6135-9_33","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"21 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NCAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Computing for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jinan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 July 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 July 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ncaa2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/dl2link.com\/ncaa2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"205","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"77","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.09","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.68","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}