{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:18:14Z","timestamp":1743110294410,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030356989"},{"type":"electronic","value":"9783030356996"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-35699-6_4","type":"book-chapter","created":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T11:34:58Z","timestamp":1575286498000},"page":"44-57","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Cooperative Multi-agent Deep Reinforcement Learning in a 2 Versus 2 Free-Kick Task"],"prefix":"10.1007","author":[{"given":"Jim Martin","family":"Catacora Ocana","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Riccio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Capobianco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,12,1]]},"reference":[{"issue":"1\u20132","key":"4_CR1","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10994-011-5235-x","volume":"84","author":"R Hafner","year":"2011","unstructured":"Hafner, R., Riedmiller, M.: Reinforcement learning in feedback control. Mach. Learn. 84(1\u20132), 137\u2013169 (2011)","journal-title":"Mach. Learn."},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Haksar, R.N., Schwager, M.: Distributed deep reinforcement learning for fighting forest fires with a network of aerial robots. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS, pp. 1067\u20131074 (2018)","DOI":"10.1109\/IROS.2018.8593539"},{"key":"4_CR3","unstructured":"Hausknecht, M.J.: Cooperation and communication in multiagent deep reinforcement learning. Ph.D. thesis, University of Texas at Austin, USA (2016)"},{"key":"4_CR4","volume-title":"Dynamic Programming and Markov Processes","author":"RA Howard","year":"1960","unstructured":"Howard, R.A.: Dynamic Programming and Markov Processes. MIT Press, Cambridge (1960)"},{"key":"4_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-642-11876-0_14","volume-title":"RoboCup 2009: Robot Soccer World Cup XIII","author":"S Kalyanakrishnan","year":"2010","unstructured":"Kalyanakrishnan, S., Stone, P.: Learning complementary multiagent behaviors: a case study. In: Baltes, J., Lagoudakis, M.G., Naruse, T., Ghidary, S.S. (eds.) RoboCup 2009. LNCS (LNAI), vol. 5949, pp. 153\u2013165. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-11876-0_14"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Knopp, M., Ayk\u0131n, C., Feldmaier, J., Shen, H.: Formation control using GQ($$\\lambda $$) reinforcement learning. In: 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pp. 1043\u20131048, August 2017","DOI":"10.1109\/ROMAN.2017.8172432"},{"key":"4_CR7","unstructured":"Kurek, M.: Deep reinforcement learning in keepaway soccer. Master\u2019s thesis, Poznan University of Technology, Poland (2015)"},{"key":"4_CR8","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. CoRR abs\/1509.02971 (2015). http:\/\/arxiv.org\/abs\/1509.02971"},{"issue":"4","key":"4_CR9","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1002\/rob.21597","volume":"33","author":"Y Liu","year":"2016","unstructured":"Liu, Y., Nejat, G.: Multirobot cooperative learning for semiautonomous control in urban search and rescue applications. J. Field Rob. 33(4), 512\u2013536 (2016)","journal-title":"J. Field Rob."},{"issue":"7540","key":"4_CR10","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":"4_CR11","unstructured":"Pham, H.X., La, H.M., Feil-Seifer, D., Nguyen, L.V.: Cooperative and distributed reinforcement learning of drones for field coverage. CoRR abs\/1803.07250 (2018). http:\/\/arxiv.org\/abs\/1803.07250"},{"key":"4_CR12","unstructured":"RoboCup Technical Committee: Robocup standard platform league (nao) rule book. Rules2018.pdf, August 2018. https:\/\/spl.robocup.org\/downloads\/"},{"key":"4_CR13","unstructured":"R\u00f6fer, T., et al.: B-human: team report and code release 2017. Technical report, Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz, Universit\u00e4t Bremen (2017)"},{"issue":"10","key":"4_CR14","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":"4_CR15","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/BF00115009","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3, 9\u201344 (1988)","journal-title":"Mach. Learn."},{"key":"4_CR16","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 1st edn. MIT Press, Cambridge (1998)","edition":"1"}],"container-title":["Lecture Notes in Computer Science","RoboCup 2019: Robot World Cup XXIII"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-35699-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T14:03:15Z","timestamp":1728309795000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-35699-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030356989","9783030356996"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-35699-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"1 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RoboCup","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Robot World Cup","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 July 2019","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":"robocup2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2019.robocup.org\/symposium.php","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":"74","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":"38","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":"0","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":"51% - 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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}