{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:21:09Z","timestamp":1742912469358,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030640958"},{"type":"electronic","value":"9783030640965"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-64096-5_6","type":"book-chapter","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T00:30:27Z","timestamp":1606264227000},"page":"69-84","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Independent Learning in Cooperative Markov Games"],"prefix":"10.1007","author":[{"given":"Roi","family":"Yehoshua","sequence":"first","affiliation":[]},{"given":"Christopher","family":"Amato","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,25]]},"reference":[{"issue":"1","key":"6_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-010-9142-5","volume":"24","author":"AK Agogino","year":"2012","unstructured":"Agogino, A.K., Tumer, K.: A multiagent approach to managing air traffic flow. Auton. Agent. Multi-Agent Syst. 24(1), 1\u201325 (2012). https:\/\/doi.org\/10.1007\/s10458-010-9142-5","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Amato, C., Dibangoye, J.S., Zilberstein, S.: Incremental policy generation for finite-horizon DEC-POMDPs. In: International Conference on Automated Planning and Scheduling (ICAPS) (2009)","DOI":"10.1609\/icaps.v19i1.13355"},{"key":"6_CR3","first-page":"746","volume":"1998","author":"C Claus","year":"1998","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. AAAI\/IAAI 1998, 746\u2013752 (1998)","journal-title":"AAAI\/IAAI"},{"key":"6_CR4","first-page":"780","volume":"2007","author":"N Fulda","year":"2007","unstructured":"Fulda, N., Ventura, D.: Predicting and preventing coordination problems in cooperative q-learning systems. Int. Joint Conf. Artif. Intell. (IJCAI). 2007, 780\u2013785 (2007)","journal-title":"Int. Joint Conf. Artif. Intell. (IJCAI)."},{"key":"6_CR5","unstructured":"Lauer, M., Riedmiller, M.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: International Conference on Machine Learning (ICML) (2000)"},{"key":"6_CR6","unstructured":"Leibo, J.Z., Zambaldi, V., Lanctot, M., Marecki, J., Graepel, T.: Multi-agent reinforcement learning in sequential social dilemmas. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 464\u2013473 (2017)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: International Conference on Machine Learning (ICML), pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: Hysteretic q-learning: an algorithm for decentralized reinforcement learning in cooperative multi-agent teams. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 64\u201369 (2007)","DOI":"10.1109\/IROS.2007.4399095"},{"issue":"1","key":"6_CR9","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."},{"issue":"1","key":"6_CR10","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1073\/pnas.36.1.48","volume":"36","author":"JF Nash","year":"1950","unstructured":"Nash, J.F.: Equilibrium points in n-person games. Proc. Natl. Acad. Sci. U.S.A. 36(1), 48\u201349 (1950)","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"6_CR11","unstructured":"Palmer, G., Savani, R., Tuyls, K.: Negative update intervals in deep multi-agent reinforcement learning. In: International Conference on Autonomous Agents and MultiAgent Systems (AAMAS), pp. 43\u201351 (2019)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Panait, L., Sullivan, K., Luke, S.: Lenient learners in cooperative multiagent systems. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 801\u2013803 (2006)","DOI":"10.1145\/1160633.1160776"},{"key":"6_CR13","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"issue":"3","key":"6_CR14","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s10458-006-9007-0","volume":"14","author":"K Verbeeck","year":"2007","unstructured":"Verbeeck, K., Now\u00e9, A., Parent, J., Tuyls, K.: Exploring selfish reinforcement learning in repeated games with stochastic rewards. Auton. Agent. Multi-Agent Syst. 14(3), 239\u2013269 (2007)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"6_CR15","first-page":"307","volume":"1","author":"P Vrancx","year":"2008","unstructured":"Vrancx, P., Tuyls, K., Westra, R.: Switching dynamics of multi-agent learning. Int. Conf. Auton. Agent. Multiagent Syst. (AAMAS) 1, 307\u2013313 (2008)","journal-title":"Int. Conf. Auton. Agent. Multiagent Syst. (AAMAS)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Wang, Y., De Silva, C.W.: Multi-robot box-pushing: single-agent q-learning vs. team q-learning. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3694\u20133699 (2006)","DOI":"10.1109\/IROS.2006.281729"},{"issue":"3\u20134","key":"6_CR17","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"issue":"1","key":"6_CR18","first-page":"2914","volume":"17","author":"E Wei","year":"2016","unstructured":"Wei, E., Luke, S.: Lenient learning in independent-learner stochastic cooperative games. J. Mach. Learn. Res. 17(1), 2914\u20132955 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR19","unstructured":"Yang, E., Gu, D.: Multiagent reinforcement learning for multi-robot systems: A survey. Technical report, Department of Computer Science, University of Essex, Technical report (2004)"}],"container-title":["Lecture Notes in Computer Science","Distributed Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-64096-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T17:25:17Z","timestamp":1669742717000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-64096-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030640958","9783030640965"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-64096-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"25 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Distributed Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"24 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dai22020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.adai.ai\/dai\/2020\/2020.html","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":"22","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":"9","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":"41% - 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":"2.77","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":"1.4","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":"Due to the Corona pandemic this event was held virtually.","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)"}}]}}