{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:47:49Z","timestamp":1757540869388,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031112164"},{"type":"electronic","value":"9783031112171"}],"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\/978-3-031-11217-1_22","type":"book-chapter","created":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T21:02:35Z","timestamp":1657918955000},"page":"301-316","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Weighted Mean-Field Multi-Agent Reinforcement Learning via\u00a0Reward Attribution Decomposition"],"prefix":"10.1007","author":[{"given":"Tingyu","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,16]]},"reference":[{"issue":"04","key":"22_CR1","doi-asserted-by":"publisher","first-page":"3414","DOI":"10.1609\/aaai.v34i04.5744","volume":"34","author":"C Chen","year":"2020","unstructured":"Chen, C., et al.: Toward a thousand lights: decentralized deep reinforcement learning for large-scale traffic signal control. AAAI 34(04), 3414\u20133421 (2020)","journal-title":"AAAI"},{"key":"22_CR2","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-981-16-2336-3_28","volume-title":"Cognitive Systems and Signal Processing","author":"B Fang","year":"2021","unstructured":"Fang, B., Wu, B., Wang, Z., Wang, H.: Large-scale multi-agent reinforcement learning based on weighted mean field. In: Sun, F., Liu, H., Fang, B. (eds.) ICCSIP 2020. CCIS, vol. 1397, pp. 309\u2013316. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-16-2336-3_28"},{"key":"22_CR3","unstructured":"Ganapathi Subramanian, S., Poupart, P., Taylor, M.E., Hegde, N.: Multi type mean field reinforcement learning. In: AAMAS (2020)"},{"key":"22_CR4","unstructured":"Ganapathi Subramanian, S., Taylor, M.E., Crowley, M., Poupart, P.: Partially observable mean field reinforcement learning. In: AAMAS (2021)"},{"key":"22_CR5","unstructured":"Guo, X., Hu, A., Xu, R., Zhang, J.: Learning mean-field games. In: NeurIPS (2019)"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: AAMAS (2017)","DOI":"10.1007\/978-3-319-71682-4_5"},{"issue":"4","key":"22_CR7","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/2829988.2790005","volume":"45","author":"SH Jeong","year":"2015","unstructured":"Jeong, S.H., Kang, A.R., Kim, H.K.: Analysis of game bot\u2019s behavioral characteristics in social interaction networks of MMORPG. ACM SIGCOMM Comput. Commun. Rev. 45(4), 99\u2013100 (2015)","journal-title":"ACM SIGCOMM Comput. Commun. Rev."},{"key":"22_CR8","unstructured":"Jiang, J., Dun, C., Huang, T., Lu, Z.: Graph convolutional reinforcement learning. In: ICLR (2020)"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Efficient ridesharing order dispatching with mean field multi-agent reinforcement learning. In: WWW (2019)","DOI":"10.1145\/3308558.3313433"},{"key":"22_CR10","unstructured":"Li, W., Wang, X., Jin, B., Sheng, J., Hua, Y., Zha, H.: Structured diversification emergence via reinforced organization control and hierarchical consensus learning. In: AAMAS (2021)"},{"key":"22_CR11","unstructured":"Li, W., Wang, X., Jin, B., Sheng, J., Zha, H.: Dealing with non-stationarity in MARL via trust region decomposition. In: ICLR (2022)"},{"key":"22_CR12","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: NeurIPS (2017)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Mao, H., et al.: Neighborhood cognition consistent multi-agent reinforcement learning. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i05.6212"},{"issue":"1","key":"22_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-020-09455-w","volume":"34","author":"H Mao","year":"2020","unstructured":"Mao, H., Zhang, Z., Xiao, Z., Gong, Z., Ni, Y.: Learning multi-agent communication with double attentional deep reinforcement learning. Autonom. Agents Multi-agent Syst. 34(1), 1\u201334 (2020). https:\/\/doi.org\/10.1007\/s10458-020-09455-w","journal-title":"Autonom. Agents Multi-agent Syst."},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.j., Le fort piat, N.: Review: Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems. Knowl. Eng. Rev. 27(1), 1\u201331 (2012)","DOI":"10.1017\/S0269888912000057"},{"issue":"7540","key":"22_CR16","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"22_CR17","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning. In: ICML (2018)"},{"key":"22_CR18","unstructured":"Ren, W.: Represented value function approach for large scale multi agent reinforcement learning. Arxiv (2020)"},{"key":"22_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108254","volume":"121","author":"J Sheng","year":"2022","unstructured":"Sheng, J., et al.: Learning to schedule multi-NUMA virtual machines via reinforcement learning. Pattern Recogn. 121, 108254 (2022)","journal-title":"Pattern Recogn."},{"key":"22_CR20","unstructured":"Sheng, J., et al.: Learning structured communication for MARL. ArXiv (2020)"},{"key":"22_CR21","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: ICML (2019)"},{"key":"22_CR22","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning based on team reward. In: AAMAS (2018)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: independent vs. cooperative agents. In: ICML (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"22_CR24","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.trc.2013.08.014","volume":"36","author":"P Varaiya","year":"2013","unstructured":"Varaiya, P.: Max pressure control of a network of signalized intersections. Transp. Res. Part C Emerg. Technol. 36, 177\u2013195 (2013)","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"22_CR25","unstructured":"Yang, F., Vereshchaka, A., Chen, C., Dong, W.: Bayesian multi-type mean field multi-agent imitation learning. In: NeurIPS (2020)"},{"key":"22_CR26","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning. In: ICML (2018)"},{"key":"22_CR27","unstructured":"Ye, D., et al.: Towards playing full MOBA games with deep reinforcement learning. In: NeurIPS (2020)"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.754"},{"key":"22_CR29","unstructured":"Zhang, T., et al.: Multi-agent collaboration via reward attribution decomposition. Arxiv (2020)"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Zheng, L., Yang, J., Cai, H., Zhou, M., Zhang, W., Wang, J., Yu, Y.: MAgent: a many-agent reinforcement learning platform for artificial collective intelligence. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, M., et al.: Multi-agent reinforcement learning for order-dispatching via order-vehicle distribution matching. In: CIKM, pp. 2645\u20132653 (2019)","DOI":"10.1145\/3357384.3357799"},{"key":"22_CR32","unstructured":"Zimmer, M., Glanois, C., Siddique, U., Weng, P.: Learning fair policies in decentralized cooperative multi-agent reinforcement learning. In: ICML (2021)"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications. DASFAA 2022 International Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-11217-1_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:13:01Z","timestamp":1710259981000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-11217-1_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031112164","9783031112171"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-11217-1_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 April 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dasfaa2022.org\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"543","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":"72","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":"76","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":"13% - 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","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":"6","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conference was originally planned to take place in Hyberabad, India. 24 other papers are included in the volume.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}