{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T15:44:12Z","timestamp":1750347852001},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540252603"},{"type":"electronic","value":"9783540322740"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/978-3-540-32274-0_8","type":"book-chapter","created":{"date-parts":[[2010,7,5]],"date-time":"2010-07-05T16:21:44Z","timestamp":1278346904000},"page":"119-131","source":"Crossref","is-referenced-by-count":13,"title":["Reinforcement Learning of Coordination in Heterogeneous Cooperative Multi-agent Systems"],"prefix":"10.1007","author":[{"given":"Spiros","family":"Kapetanakis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","unstructured":"Boutilier, C.: Sequential optimality and coordination in multiagent systems. In: Proceedings of the Sixteenth International Joint Conference on Articial Intelligence (IJCAI 1999), pp. 478\u2013485 (1999)"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Chalkiadakis, G., Boutilier, C.: Coordination in multiagent reinforcement learning: A bayesian approach. In: Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, Melbourne, Australia, pp. 709\u2013716 (2003)","DOI":"10.1145\/860575.860689"},{"key":"8_CR3","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Articial Intelligence, pp. 746\u2013752 (1998)"},{"key":"8_CR4","volume-title":"The Theory of Learning in Games","author":"D. Fudenberg","year":"1998","unstructured":"Fudenberg, D., Levine, D.K.: The Theory of Learning in Games. MIT Press, Cambridge (1998)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P., Littman, M., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research\u00a04 (1996)","DOI":"10.1613\/jair.301"},{"key":"8_CR6","unstructured":"Kapetanakis, S., Kudenko, D.: Reinforcement learning of coordination in cooperative multi-agent systems. In: Proceedings of the Nineteenth National Conference on Artificial Intelligence, Edmonton, Alberta, Canada, pp. 326\u2013331 (2002)"},{"key":"8_CR7","unstructured":"Kapetanakis, S., Kudenko, D., Strens, M.: Learning to coordinate using commitment sequences in cooperative multi-agent systems. In: Proceedings of the Third Symposium on Adaptive Agents and Multi-agent Systems (AAMAS 2003), Society for the study of Artificial Intelligence and Simulation of Behaviour (2003)"},{"key":"8_CR8","unstructured":"Lauer, M., Riedmiller, M.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: Proceedings of the Seventeenth International Conference in Machine Learning (2000)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Kaufman, M. (ed.) Proceedings of the Eleventh International Conference on Machine Learning, San Mateo, CA, USA, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"issue":"3","key":"8_CR10","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1080\/095281398146798","volume":"10","author":"S. Sen","year":"1998","unstructured":"Sen, S., Sekaran, M.: Individual learning of coordination knowledge. JETAI\u00a010(3), 333\u2013356 (1998)","journal-title":"JETAI"},{"key":"8_CR11","first-page":"97","volume-title":"Proceedings of Third Symposium on Adaptive Agents and Multi-agent Systems","author":"K. Verbeeck","year":"2003","unstructured":"Verbeeck, K., Nowe, A., Tuyls, K.: Coordinated exploration in stochastic common interest games. In: Proceedings of Third Symposium on Adaptive Agents and Multi-agent Systems, pp. 97\u2013102. University of Wales, Aberystwyth (2003)"},{"key":"8_CR12","unstructured":"Wang, X., Sandholm, T.: Reinforcement learning to play an optimal nash equilibrium in team markov games. In: Proceedings of the 16th Neural Information Processing Systems: Natural and Synthetic conference, Vancouver, Canada (2002)"}],"container-title":["Lecture Notes in Computer Science","Adaptive Agents and Multi-Agent Systems II"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-32274-0_8.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,2]],"date-time":"2021-05-02T23:46:51Z","timestamp":1619999211000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-32274-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540252603","9783540322740"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-32274-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}