{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T12:39:40Z","timestamp":1725539980561},"publisher-location":"London","reference-count":6,"publisher":"Springer London","isbn-type":[{"type":"print","value":"9781848829824"},{"type":"electronic","value":"9781848829831"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-1-84882-983-1_21","type":"book-chapter","created":{"date-parts":[[2009,10,27]],"date-time":"2009-10-27T12:58:27Z","timestamp":1256648307000},"page":"293-298","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Agent Reinforcement Learning \u2013 An Exploration Using Q-Learning"],"prefix":"10.1007","author":[{"given":"Caoimh\u00edn","family":"Graham","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Bell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihui","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,10,19]]},"reference":[{"key":"21_CR1","unstructured":"Puterman,M.L., Markov Decision Processes: Discrete Stochastic Dynamic Programming. 2005: Wiley-Interscience"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Sutton,R. & Barto,A., Reinforcement Learning: An Introduction. 1998: MIT Press","DOI":"10.1109\/TNN.1998.712192"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Watkins,C. & Dayan,P., Q-Learning. Machine Learning, 8(3-4):279\u2013292, 1992, 1992","DOI":"10.1023\/A:1022676722315"},{"key":"21_CR4","unstructured":"Bell, Luo & McCollum, Skill Combination in Reinforcement Learning, 2008"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Tesauro,G. Temporal Difference Learning & TD-Gammon, 1995","DOI":"10.3233\/ICG-1995-18207"},{"key":"21_CR6","unstructured":"Agogino,A. & Tumer,K, Quicker Q-Learning in Multi-Agent Systems, 2008"}],"container-title":["Research and Development in Intelligent Systems XXVI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-84882-983-1_21.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T15:06:26Z","timestamp":1605711986000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-1-84882-983-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,10,19]]},"ISBN":["9781848829824","9781848829831"],"references-count":6,"URL":"https:\/\/doi.org\/10.1007\/978-1-84882-983-1_21","relation":{},"subject":[],"published":{"date-parts":[[2009,10,19]]}}}