{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T07:09:25Z","timestamp":1769238565911,"version":"3.49.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031442223","type":"print"},{"value":"9783031442230","type":"electronic"}],"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_4","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T05:01:41Z","timestamp":1695272501000},"page":"37-48","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Group-Agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Kaiyue","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Jun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"4_CR1","volume-title":"Social Learning Theory","author":"A Bandura","year":"1977","unstructured":"Bandura, A., Walters, R.H.: Social Learning Theory, vol. 1. Prentice Hall, Englewood Cliffs (1977)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bellman, R.: A Markovian decision process. J. Math. Mech. 6(5), 679\u2013684 (1957). http:\/\/www.jstor.org\/stable\/24900506","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Bu\u015foniu, L., Babu\u0161ka, R., Schutter, B.D.: Multi-agent reinforcement learning: an overview. In: Innovations in Multi-Agent Systems and Applications-1, pp. 183\u2013221 (2010)","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"4_CR4","unstructured":"Denoyer, L., de la Fuente, A., Duong, S., Gaya, J.B., Kamienny, P.A., Thompson, D.H.: Salina: sequential learning of agents (2021). https:\/\/github.com\/facebookresearch\/salina"},{"key":"4_CR5","unstructured":"Foerster, J., et al.: Stabilising experience replay for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 1146\u20131155. PMLR (2017)"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Guo, X., Chang, S., Yu, M., Tesauro, G., Campbell, M.: Hybrid reinforcement learning with expert state sequences. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3739\u20133746 (2019)","DOI":"10.1609\/aaai.v33i01.33013739"},{"key":"4_CR7","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":"4_CR8","unstructured":"Luo, M., Yao, J., Liaw, R., Liang, E., Stoica, I.: Impact: importance weighted asynchronous architectures with clipped target networks (2020)"},{"key":"4_CR9","unstructured":"Ma, X., Yang, Y., Li, C., Lu, Y., Zhao, Q., Jun, Y.: Modeling the interaction between agents in cooperative multi-agent reinforcement learning. arXiv preprint arXiv:2102.06042 (2021)"},{"issue":"1","key":"4_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0269888912000057","volume":"27","author":"L Matignon","year":"2012","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems. Knowl. Eng. Rev. 27(1), 1\u201331 (2012)","journal-title":"Knowl. Eng. Rev."},{"key":"4_CR11","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"issue":"7540","key":"4_CR12","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). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"4_CR13","unstructured":"Nair, A., et al.: Massively parallel methods for deep reinforcement learning (2015)"},{"key":"4_CR14","unstructured":"Ndousse, K.K., Eck, D., Levine, S., Jaques, N.: Emergent social learning via multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 7991\u20138004. PMLR (2021)"},{"key":"4_CR15","unstructured":"Omidshafiei, S., Pazis, J., Amato, C., How, J.P., Vian, J.: Deep decentralized multi-task multi-agent reinforcement learning under partial observability. In: International Conference on Machine Learning, pp. 2681\u20132690. PMLR (2017)"},{"issue":"19","key":"4_CR16","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023","volume":"2017","author":"AE Sallab","year":"2017","unstructured":"Sallab, A.E., Abdou, M., Perot, E., Yogamani, S.: Deep reinforcement learning framework for autonomous driving. Electron. Imaging 2017(19), 70\u201376 (2017)","journal-title":"Electron. Imaging"},{"key":"4_CR17","unstructured":"Samsami, M.R., Alimadad, H.: Distributed deep reinforcement learning: an overview. CoRR abs\/2011.11012 (2020). arxiv.org\/abs\/2011.11012"},{"key":"4_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017)"},{"key":"4_CR19","unstructured":"Stadie, B.C., Abbeel, P., Sutskever, I.: Third-person imitation learning. arXiv preprint arXiv:1703.01703 (2017)"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Vithayathil Varghese, N., Mahmoud, Q.H.: A survey of multi-task deep reinforcement learning. Electronics 9(9), 1363 (2020)","DOI":"10.3390\/electronics9091363"},{"key":"4_CR21","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":"4_CR22","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards (1989)"},{"key":"4_CR23","unstructured":"Wijmans, E., et al.: DD-PPO: learning near-perfect PointGoal navigators from 2.5 billion frames (2020)"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., Basar, T.: Networked multi-agent reinforcement learning in continuous spaces. In: 2018 IEEE Conference on Decision and Control (CDC), pp. 2771\u20132776. IEEE (2018)","DOI":"10.1109\/CDC.2018.8619581"}],"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_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T06:10:47Z","timestamp":1695276647000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44223-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442223","9783031442230"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44223-0_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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)"}}]}}