{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:06:00Z","timestamp":1743080760176,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031159305"},{"type":"electronic","value":"9783031159312"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-15931-2_2","type":"book-chapter","created":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T05:03:47Z","timestamp":1662440627000},"page":"14-25","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cooperative Multi-agent Reinforcement Learning with\u00a0Hierachical Communication Architecture"],"prefix":"10.1007","author":[{"given":"Shifan","family":"Liu","sequence":"first","affiliation":[]},{"given":"Quan","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Guiyang","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Jinglin","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,7]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Bacon, P.L., Harb, J., Precup, D.: The option-critic architecture. In: Proceedings of the AAAI, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.10916"},{"issue":"1","key":"2_CR2","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TII.2012.2219061","volume":"9","author":"Y Cao","year":"2012","unstructured":"Cao, Y., Yu, W., Ren, W., Chen, G.: An overview of recent progress in the study of distributed multi-agent coordination. IEEE Trans. Ind. Inform. 9(1), 427\u2013438 (2012)","journal-title":"IEEE Trans. Ind. Inform."},{"key":"2_CR3","unstructured":"Chu, T., Chinchali, S., Katti, S.: Multi-agent reinforcement learning for networked system control. In: Proceedings of the ICLR (2019)"},{"key":"2_CR4","unstructured":"Das, A., Gervet, T., Romoff, J., Batra, D., Parikh, D., Rabbat, M., Pineau, J.: Tarmac: targeted multi-agent communication. In: Proceeding of the ICML, pp. 1538\u20131546. PMLR (2019)"},{"key":"2_CR5","unstructured":"Foerster, J., Assael, I.A., De Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Harb, J., Bacon, P.L., Klissarov, M., Precup, D.: When waiting is not an option: learning options with a deliberation cost. In: Proceedings of the AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11831"},{"key":"2_CR8","unstructured":"Hoshen, Y.: Vain: attentional multi-agent predictive modeling. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR9","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"2_CR10","unstructured":"Kim, D., Moon, S., Hostallero, D., Kang, W.J., Lee, T., Son, K., Yi, Y.: Learning to schedule communication in multi-agent reinforcement learning. In: Proceedings of the ICLR (2018)"},{"key":"2_CR11","unstructured":"Kulkarni, T.D., Narasimhan, K., Saeedi, A., Tenenbaum, J.: Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"2_CR12","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":"2_CR13","unstructured":"Peng, P., et al.: Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games. arXiv:1703.10069 (2017)"},{"key":"2_CR14","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: Proceedings of the ICML, vol. 80, pp. 4295\u20134304 (2018)"},{"key":"2_CR15","unstructured":"Singh, A., Jain, T., Sukhbaatar, S.: Learning when to communicate at scale in multiagent cooperative and competitive tasks. In: Proceedings of the IMCL (2018)"},{"key":"2_CR16","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: Proceedings of the ICML, vol. 97, pp. 5887\u20135896 (2019)"},{"key":"2_CR17","unstructured":"Sukhbaatar, S., Fergus, R., et al.: Learning multiagent communication with backpropagation. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"issue":"1\u20132","key":"2_CR18","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"2_CR19","unstructured":"Vezhnevets, A.S., et al.: Feudal networks for hierarchical reinforcement learning. In: Proceedings of the ICML, pp. 3540\u20133549 (2017)"},{"key":"2_CR20","unstructured":"Vinyals, O., et al.: Starcraft ii: a new challenge for reinforcement learning. arXiv:1708.04782 (2017)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15931-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T18:04:01Z","timestamp":1680631441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15931-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031159305","9783031159312"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15931-2_2","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":"7 September 2022","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":"Bristol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"6 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2022\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"561","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":"255","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":"4","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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}