{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:14:12Z","timestamp":1742933652348,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319973098"},{"type":"electronic","value":"9783319973104"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-97310-4_15","type":"book-chapter","created":{"date-parts":[[2018,7,26]],"date-time":"2018-07-26T16:06:19Z","timestamp":1532621179000},"page":"132-139","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Achieving Multiagent Coordination Through CALA-rFMQ Learning in Continuous Action Space"],"prefix":"10.1007","author":[{"given":"Wanshu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianpei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijie","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,7,27]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9052-5","volume-title":"Networks of Learning Automata: Techniques for Online Stochastic Optimization","author":"M Thathachar","year":"2004","unstructured":"Thathachar, M., Sastry, P.: Networks of Learning Automata: Techniques for Online Stochastic Optimization. Kluwer Academic Publishers, Boston (2004)"},{"issue":"2","key":"15_CR2","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M Bowling","year":"2002","unstructured":"Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artif. Intell. 136(2), 215\u2013250 (2002)","journal-title":"Artif. Intell."},{"issue":"1","key":"15_CR3","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1017\/S026988890500041X","volume":"20","author":"K Tuyls","year":"2005","unstructured":"Tuyls, K., Now, A.: Evolutionary game theory and multi-agent reinforcement learning. Knowl. Eng. Rev. 20(1), 63\u201390 (2005)","journal-title":"Knowl. Eng. Rev."},{"unstructured":"Kapetanakis, S., Kudenko, D.: Reinforcement learning of coordination in cooperative multi-agent systems. In: AAAI\/IAAI, pp. 326\u2013331 (2002)","key":"15_CR4"},{"issue":"1","key":"15_CR5","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":"15_CR6","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.engappai.2016.11.008","volume":"58","author":"J Hao","year":"2017","unstructured":"Hao, J., Huang, D., Cai, Y., et al.: The dynamics of reinforcement social learning in networked cooperative multiagent systems. Eng. Appl. Artifi. Intell. 58, 111\u2013122 (2017)","journal-title":"Eng. Appl. Artifi. Intell."},{"unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence, pp. 746\u2013752 (1998)","key":"15_CR7"},{"unstructured":"Lauer, M., Riedmiller, M.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: Proceedings of the Seventeenth International Conference on Machine Learning (2000)","key":"15_CR8"},{"unstructured":"Chen, X., Duan, Y., Houthooft, R., et al.: Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172\u20132180 (2016)","key":"15_CR9"},{"key":"15_CR10","volume-title":"Numerical Analysis with Algorithms and Programming","author":"SS Ray","year":"2016","unstructured":"Ray, S.S.: Numerical Analysis with Algorithms and Programming. CRC Press, Boca Raton (2016)"},{"key":"15_CR11","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.engappai.2017.12.004","volume":"69","author":"E Alibekov","year":"2018","unstructured":"Alibekov, E., Kubalk, J., Babuka, R.: Policy derivation methods for critic-only reinforcement learning in continuous spaces. Eng. Appl. Artif. Intell. 69, 178\u2013187 (2018)","journal-title":"Eng. Appl. Artif. Intell."},{"doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Maei, H.R., Precup, D., et al.: Fast gradient-descent methods for temporal-difference learning with linear function approximation. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 993\u20131000. ACM (2009)","key":"15_CR12","DOI":"10.1145\/1553374.1553501"},{"issue":"1","key":"15_CR13","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/s10458-011-9181-6","volume":"26","author":"A Galstyan","year":"2013","unstructured":"Galstyan, A.: Continuous strategy replicator dynamics for multi-agent Q-learning. Auton. Agents Multi-Agent Syst. 26(1), 37\u201353 (2013)","journal-title":"Auton. Agents Multi-Agent Syst."},{"unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)","key":"15_CR14"},{"issue":"4","key":"15_CR15","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1016\/j.neunet.2008.02.003","volume":"21","author":"J Peters","year":"2008","unstructured":"Peters, J., Schaal, S.: Reinforcement learning of motor skills with policy gradients. Neural Netw. 21(4), 682\u2013697 (2008)","journal-title":"Neural Netw."},{"key":"15_CR16","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-642-27645-3_7","volume-title":"Reinforcement Learning","author":"H Van Hasselt","year":"2012","unstructured":"Van Hasselt, H.: Reinforcement learning in continuous state and action spaces. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning, pp. 207\u2013251. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_7"},{"doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-Learning. In: AAAI 2016, pp. 2094\u20132100 (2016)","key":"15_CR17","DOI":"10.1609\/aaai.v30i1.10295"},{"unstructured":"Lazaric, A., Restelli, M., Bonarini, A.: Reinforcement learning in continuous action spaces through sequential Monte Carlo methods. In: Advances in Neural Information Processing Systems, pp. 833\u2013840 (2008)","key":"15_CR18"},{"unstructured":"De Jong, S., Tuyls, K., Verbeeck, K.: Artificial agents learning human fairness. In: Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2008, vol. 2, pp. 863\u2013870 (2008)","key":"15_CR19"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2018: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-97310-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:11:07Z","timestamp":1709827867000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-97310-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319973098","9783319973104"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-97310-4_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"27 July 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on 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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/cse.seu.edu.cn\/pricai18\/","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":"382","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":"82","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":"58","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":"21% - 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":"2.95","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":"2.95","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)"}}]}}