{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T19:02:53Z","timestamp":1743015773010,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442223"},{"type":"electronic","value":"9783031442230"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44223-0_10","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T05:01:41Z","timestamp":1695272501000},"page":"115-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pacesetter Learning for\u00a0Large Scale Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Pingqi","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengwei","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chennan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"10_CR1","unstructured":"Ancona, M., Ceolini, E., \u00d6ztireli, C., Gross, M.: Towards better understanding of gradient-based attribution methods for deep neural networks. arXiv preprint arXiv:1711.06104 (2017)"},{"key":"10_CR2","unstructured":"Jeon, J., Kim, W., Jung, W., Sung, Y.: MASER: multi-agent reinforcement learning with subgoals generated from experience replay buffer. In: International Conference on Machine Learning, pp. 10041\u201310052. PMLR (2022)"},{"key":"10_CR3","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Kong, X., Xin, B., Wang, Y., Hua, G.: Collaborative deep reinforcement learning for joint object search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1695\u20131704 (2017)","DOI":"10.1109\/CVPR.2017.748"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Lin, K., Zhao, R., Xu, Z., Zhou, J.: Efficient large-scale fleet management via multi-agent deep reinforcement learning. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1774\u20131783 (2018)","DOI":"10.1145\/3219819.3219993"},{"key":"10_CR6","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Mao, H., Zhang, Z., Xiao, Z., Gong, Z., Ni, Y.: Learning agent communication under limited bandwidth by message pruning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5142\u20135149 (2020)","DOI":"10.1609\/aaai.v34i04.5957"},{"key":"10_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"FA Oliehoek","year":"2016","unstructured":"Oliehoek, F.A., Amato, C.: A Concise Introduction to Decentralized POMDPs. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-28929-8"},{"key":"10_CR9","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"10_CR10","first-page":"10199","volume":"33","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Farquhar, G., Peng, B., Whiteson, S.: 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."},{"issue":"1","key":"10_CR11","first-page":"7234","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Samvelyan, M., De Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21(1), 7234\u20137284 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR12","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)"},{"key":"10_CR13","unstructured":"Shalev-Shwartz, S., Shammah, S., Shashua, A.: Safe, multi-agent, reinforcement learning for autonomous driving. arXiv preprint arXiv:1610.03295 (2016)"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Shamsoshoara, A., Khaledi, M., Afghah, F., Razi, A., Ashdown, J.: Distributed cooperative spectrum sharing in UAV networks using multi-agent reinforcement learning. In: 2019 16th IEEE Annual Consumer Communications & Networking Conference (CCNC), pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/CCNC.2019.8651796"},{"issue":"10","key":"10_CR15","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1073\/pnas.39.10.1095","volume":"39","author":"LS Shapley","year":"1953","unstructured":"Shapley, L.S.: Stochastic games. Proc. Natl. Acad. Sci. 39(10), 1095\u20131100 (1953)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10_CR16","unstructured":"Siqi, S., et al.: ResQ: a residual Q function-based approach for multi-agent reinforcement learning value factorization. In: Thirty-Sixth Conference on Neural Information Processing Systems (2022)"},{"key":"10_CR17","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: International Conference on Machine Learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Spaan, M.T.: Partially observable Markov decision processes. In: Reinforcement Learning: State-of-the-Art, pp. 387\u2013414 (2012)","DOI":"10.1007\/978-3-642-27645-3_12"},{"key":"10_CR19","volume-title":"Phase Transitions and Critical Phenomena","author":"HE Stanley","year":"1971","unstructured":"Stanley, H.E.: Phase Transitions and Critical Phenomena, vol. 7. Clarendon Press, Oxford (1971)"},{"key":"10_CR20","unstructured":"Sun, W.F., Lee, C.K., Lee, C.Y.: DFAC framework: factorizing the value function via quantile mixture for multi-agent distributional Q-learning. In: International Conference on Machine Learning, pp. 9945\u20139954. PMLR (2021)"},{"key":"10_CR21","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"10_CR22","unstructured":"Wan, L., Liu, Z., Chen, X., Lan, X., Zheng, N.: Greedy based value representation for optimal coordination in multi-agent reinforcement learning. arXiv preprint arXiv:2211.12075 (2022)"},{"key":"10_CR23","unstructured":"Wang, J., Ren, Z., Liu, T., Yu, Y., Zhang, C.: QPLEX: duplex dueling multi-agent Q-learning. arXiv preprint arXiv:2008.01062 (2020)"},{"key":"10_CR24","unstructured":"Yang, Y., et al.: Qatten: a general framework for cooperative multiagent reinforcement learning. arXiv preprint arXiv:2002.03939 (2020)"},{"key":"10_CR25","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5571\u20135580. PMLR (2018)"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., Ba\u015far, T.: Multi-agent reinforcement learning: a selective overview of theories and algorithms. In: Handbook of Reinforcement Learning and Control, pp. 321\u2013384 (2021)","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Zohar, R., Mannor, S., Tennenholtz, G.: Locality matters: a scalable value decomposition approach for cooperative multi-agent reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 9278\u20139285 (2022)","DOI":"10.1609\/aaai.v36i8.20915"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44223-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T06:12:02Z","timestamp":1695276722000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44223-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442223","9783031442230"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44223-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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)"}},{"value":"type of other papers accepted  : 9 Abstract","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)"}}]}}