{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:56:29Z","timestamp":1725558989854},"publisher-location":"Berlin, Heidelberg","reference-count":6,"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_4","type":"book-chapter","created":{"date-parts":[[2010,7,5]],"date-time":"2010-07-05T16:21:44Z","timestamp":1278346904000},"page":"55-72","source":"Crossref","is-referenced-by-count":2,"title":["Baselines for Joint-Action Reinforcement Learning of Coordination in Cooperative Multi-agent Systems"],"prefix":"10.1007","author":[{"given":"Martin","family":"Carpenter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"4_CR1","unstructured":"Wang, X., Sandholm, T.: Reinforcement learning to play an optimal nash equilibrium in team markov games. In: Proceedings of the Sixteenth Conference on Neural Information Processing Systems (2002)"},{"key":"4_CR2","unstructured":"Kapetanakis, S., Kudenko, D.: Reinforcement learning of coordination in cooperative multiagent systems. In: Proceedings of the Eighteenth National Conference on Artifical Intelligence (2002)"},{"key":"4_CR3","unstructured":"Claus, C., Boutilier, C.: Dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artifical Intelligence 1998(1998)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Chalkiadakis, G., Boutilier, C.: Coordination in multiagent reinforcement learning: A bayesian approach. In: Proceedings of the Second international conference on Automonous Agents and Multiagent Systems (2003)","DOI":"10.1145\/860575.860689"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi - agent reinforcement learning. In: Proceedings of the Eleventh International Conference on machine Learning (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"4_CR6","unstructured":"Watkins, C.: Learning from Delayed Rewards. PhD thesis, King\u2019s College, Cambridge University (1989)"}],"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_4.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,2]],"date-time":"2021-05-02T23:46:50Z","timestamp":1619999210000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-32274-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540252603","9783540322740"],"references-count":6,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-32274-0_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}