{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T19:15:04Z","timestamp":1726514104319},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540400684"},{"type":"electronic","value":"9783540448266"}],"license":[{"start":{"date-parts":[[2003,1,1]],"date-time":"2003-01-01T00:00:00Z","timestamp":1041379200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2003,1,1]],"date-time":"2003-01-01T00:00:00Z","timestamp":1041379200000},"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":[[2003]]},"DOI":"10.1007\/3-540-44826-8_2","type":"book-chapter","created":{"date-parts":[[2007,7,3]],"date-time":"2007-07-03T15:50:25Z","timestamp":1183477825000},"page":"18-32","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Reinforcement Learning Approaches to Coordination in Cooperative Multi-agent Systems"],"prefix":"10.1007","author":[{"given":"Spiros","family":"Kapetanakis","sequence":"first","affiliation":[]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[]},{"given":"Malcolm J. A.","family":"Strens","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2003,5,13]]},"reference":[{"key":"2_CR1","unstructured":"C. Boutilier. Sequential optimality and coordination in multiagent systems. In Proceedings of the Sixteenth International Joint Conference on Articial Intelligence (IJCAI-99), pages 478\u2013485, 1999."},{"key":"2_CR2","unstructured":"Caroline Claus and Craig Boutilier. The dynamics of reinforcement learning in cooperative multiagent systems. In Proceedings of the Fifteenth National Conference on Articial Intelligence, pages 746\u2013752, 1998."},{"volume-title":"The Theory of Learning in Games","year":"1998","author":"D. Fudenberg","key":"2_CR3","unstructured":"Drew Fudenberg and David K. Levine. The Theory of Learning in Games. MIT Press, Cambridge, MA, 1998."},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Leslie Pack Kaelbling, Michael Littman, and Andrew W. Moore. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4, 1996.","DOI":"10.1613\/jair.301"},{"key":"2_CR5","unstructured":"Martin Lauer and Martin Riedmiller. An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In Proceedings of the Seventeenth International Conference in Machine Learning, 2000."},{"issue":"3","key":"2_CR6","first-page":"333","volume":"10","author":"S. Sen","year":"1998","unstructured":"Sandip Sen and Mahendra Sekaran. Individual learning of coordination knowledge. JETAI, 10(3): 333\u2013356, 1998.","journal-title":"JETAI"},{"key":"2_CR7","unstructured":"Sandip Sen, Mahendra Sekaran, and John Hale. Learning to coordinate without sharing information. In Proceedings of the Twelfth National Conference on Artificial Intelligence, pages 426\u2013431, Seattle, WA, 1994."},{"issue":"3","key":"2_CR8","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1023\/A:1007678930559","volume":"38","author":"S. Singh","year":"2000","unstructured":"S. Singh, T. Jaakkola, M. L. Littman, and C Szpesvari. Convergence results for single-step on-policy reinforcement-learning algorithms. Machine Learning Journal, 38(3):287\u2013308, 2000.","journal-title":"Machine Learning Journal"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Ming Tan. Multi-agent reinforcement learning: Independent vs. cooperative agents. In Proceedings of the Tenth International Conference on Machine Learning, pages 330\u2013337, 1993.","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"volume-title":"Learning from Delayed Rewards","year":"1989","author":"C. J. C. H. Watkins","key":"2_CR10","unstructured":"C. J. C. H. Watkins. Learning from Delayed Rewards. PhD thesis, Cambridge University, Cambridge, England, 1989."},{"key":"2_CR11","first-page":"311","volume":"1","author":"G. Weiss","year":"1993","unstructured":"Gerhard Weiss. Learning to coordinate actions in multi-agent systems. In Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, volume 1, pages 311\u2013316. Morgan Kaufmann Publ., 1993.","journal-title":"Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence"}],"container-title":["Lecture Notes in Computer Science","Adaptive Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-44826-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T18:29:10Z","timestamp":1675189750000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/3-540-44826-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540400684","9783540448266"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/3-540-44826-8_2","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2003]]},"assertion":[{"value":"13 May 2003","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}