{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T14:48:59Z","timestamp":1749221339989},"publisher-location":"Berlin, Heidelberg","reference-count":8,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540609230"},{"type":"electronic","value":"9783540497264"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1996]]},"DOI":"10.1007\/3-540-60923-7_21","type":"book-chapter","created":{"date-parts":[[2012,2,26]],"date-time":"2012-02-26T21:04:47Z","timestamp":1330290287000},"page":"97-112","source":"Crossref","is-referenced-by-count":2,"title":["A framework for distributed reinforcement learning"],"prefix":"10.1007","author":[{"given":"Pan","family":"Gu","sequence":"first","affiliation":[]},{"given":"Anthony B.","family":"Maddox","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2005,6,1]]},"reference":[{"key":"6_CR1","volume-title":"Flexible manufacturing cells and systems","author":"W. W. Luggen","year":"1991","unstructured":"Luggen, W. W. (1991). Flexible manufacturing cells and systems. Printice Hall, Englewood Cliffs, NJ."},{"key":"6_CR2","volume-title":"Technical report","author":"P. Gu","year":"1994","unstructured":"Gu, P. & Maddox, A. B. (1994). A protocol for mutisensor interpretation. Technical report. Department of IE\/IS, Northeastern University, Boston, MA."},{"issue":"2","key":"6_CR3","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L. R. Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A Tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of IEEE, 77(2), pp. 257\u2013286.","journal-title":"Proceedings of IEEE"},{"key":"6_CR4","unstructured":"Sian, S. S. (1991). Adaptation based on cooperative learning in multi-agent systems. Decentralized A.I. \u2014 2, In Yves Demazeau & Jean-Pierre Muller (eds.). Elsevier Science Publishers B. V. pp. 257\u2013273."},{"key":"6_CR5","first-page":"330","volume-title":"ML-93","author":"M. Tan","year":"1993","unstructured":"Tan, M. (1993). Multi-agent reinforcement learning: independent vs. cooperative agents. ML-93. University of Massachusetts, Amherst. pp. 330\u2013337."},{"key":"6_CR6","first-page":"279","volume":"8","author":"C. J. C. H. Watkins","year":"1992","unstructured":"Watkins, C. J. C. H. & Dayan, P. (1992.) Technical note: Q-Learning. Machine Learning, 8, pp. 279\u2013292.","journal-title":"Machine Learning"},{"key":"6_CR7","unstructured":"Weib, G. (1993). Learning to coordinate actions in multi-agent systems. 13th International Joint Conference on Artificial Intelligence (IJCAI-93), France, pp. 311\u2013316."},{"key":"6_CR8","first-page":"45","volume":"7","author":"S. D. Whitehead","year":"1991","unstructured":"Whitehead S. D. & Ballard D. H. (1991). Learning to perceive and act by trial and error. Machine Learning, 7. pp. 45\u201383,.","journal-title":"Machine Learning"}],"container-title":["Lecture Notes in Computer Science","Adaption and Learning in Multi-Agent Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-60923-7_21.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,28]],"date-time":"2021-04-28T01:28:14Z","timestamp":1619573294000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-60923-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1996]]},"ISBN":["9783540609230","9783540497264"],"references-count":8,"URL":"https:\/\/doi.org\/10.1007\/3-540-60923-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1996]]}}}