{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:27:51Z","timestamp":1763202471403,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030693213"},{"type":"electronic","value":"9783030693220"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69322-0_10","type":"book-chapter","created":{"date-parts":[[2021,2,14]],"date-time":"2021-02-14T08:44:56Z","timestamp":1613292296000},"page":"150-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Analysis of Coordination Structures of Partially Observing Cooperative Agents by Multi-agent Deep Q-Learning"],"prefix":"10.1007","author":[{"given":"Ken","family":"Smith","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Miyashita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9271-4507","authenticated-orcid":false,"given":"Toshiharu","family":"Sugawara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,14]]},"reference":[{"key":"10_CR1","unstructured":"Foerster, J.N., Assael, Y.M., de Freitas, N., Whiteson, S.: Learning to communicate to solve riddles with deep distributed recurrent Q-networks. CoRR, vol. abs\/1602.02672 (2016)"},{"key":"10_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","volume-title":"Autonomous Agents and Multiagent Systems","author":"JK Gupta","year":"2017","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: Sukthankar, G., Rodriguez-Aguilar, J.A. (eds.) AAMAS 2017. LNCS (LNAI), vol. 10642, pp. 66\u201383. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-71682-4_5"},{"key":"10_CR3","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. CoRR, vol. abs\/1706.02275 (2017)"},{"key":"10_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/978-3-030-30487-4_42","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Theoretical Neural Computation","author":"Y Miyashita","year":"2019","unstructured":"Miyashita, Y., Sugawara, T.: Cooperation and coordination regimes by deep Q-learning in multi-agent task executions. In: Tetko, I.V., Kurkov\u00e1, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11727, pp. 541\u2013554. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30487-4_42"},{"key":"10_CR5","unstructured":"Leibo, J.Z., Zambaldi, V., Lanctot, M., Marecki, J., Graepel, T.: Multi-agent reinforcement learning in sequential social dilemmas. In: International Foundation for Autonomous Agents and Multiagent Systems, ser. AAMAS 2017, Richland, SC, pp. 464\u2013473 (2017)"},{"key":"10_CR6","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. CoRR, vol. abs\/1509.02971 (2015)"},{"key":"10_CR7","unstructured":"van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. CoRR, vol. abs\/1509.06461 (2015)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Lample, G., Chaplot, D.S.: Playing FPS games with deep reinforcement learning. CoRR, vol. abs\/1609.05521 (2016)","DOI":"10.1609\/aaai.v31i1.10827"},{"issue":"7540","key":"10_CR9","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":"10_CR10","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. CoRR, vol. abs\/1312.5602 (2013)"},{"key":"10_CR11","unstructured":"Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., De Freitas, N.: Dueling network architectures for deep reinforcement learning. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ser. ICML 2016. JMLR.org, pp. 1995\u20132003 (2016)"},{"key":"10_CR12","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent Q-learning for partially observable MDPs. CoRR, vol. abs\/1507.06527 (2015)"},{"key":"10_CR13","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI 2018), New Orleans, Louisiana, USA, 2\u20137 February 2018, pp. 3215\u20133222. AAAI Press (2018)"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Diallo, E.A.O., Sugawara, T.: Coordination in adversarial multi-agent with deep reinforcement learning under partial observability. In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI) (2019)","DOI":"10.1109\/ICTAI.2019.00036"},{"key":"10_CR15","unstructured":"Chollet, F., et al.: Keras (2015). https:\/\/github.com\/fchollet\/keras"},{"key":"10_CR16","unstructured":"Tieleman, T., Hinton, G.: Neural Networks for Machine Learning - Lecture 6a - Overview of mini-batch gradient descent (2012)"}],"container-title":["Lecture Notes in Computer Science","PRIMA 2020: Principles and Practice of Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69322-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T07:51:00Z","timestamp":1671263460000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69322-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030693213","9783030693220"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69322-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"14 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRIMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Principles and Practice of Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nagoya","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"prima2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/uchiya.web.nitech.ac.jp\/prima2020\/","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":"50","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":"19","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":"13","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","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":"2","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)"}}]}}