{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:33:30Z","timestamp":1761597210295},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540654773"},{"type":"electronic","value":"9783540492412"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1998]]},"DOI":"10.1007\/10693067_4","type":"book-chapter","created":{"date-parts":[[2010,7,1]],"date-time":"2010-07-01T22:33:09Z","timestamp":1278023589000},"page":"45-57","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Agent Reinforcement Learning System Integrating Exploitation- and Exploration-Oriented Learning"],"prefix":"10.1007","author":[{"given":"Satoshi","family":"Kurihara","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toshiharu","family":"Sugawara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rikio","family":"Onai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"1-2","key":"4_CR1","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/0004-3702(94)00011-O","volume":"72","author":"A.G. Barto","year":"1995","unstructured":"Barto, A.G., Bradtke, S.J., Singh, S.P.: Learning to act using real-time dynamic programing. Artificial Intelligence\u00a072(1-2), 81\u2013138 (1995)","journal-title":"Artificial Intelligence"},{"key":"4_CR2","first-page":"55","volume":"8","author":"C.J.C. Watkins","year":"1992","unstructured":"Watkins, C.J.C., Dayan, P.: Technical Note: Q-Learning. Machine Learning\u00a08, 55\u201368 (1992)","journal-title":"Machine Learning"},{"key":"4_CR3","first-page":"225","volume":"3","author":"J.J. Grefenstette","year":"1988","unstructured":"Grefenstette, J.J.: Credit Assignment in Rule Discovery Systems Based on Generic Algorithms. Machine Learning\u00a03, 225\u2013245 (1988)","journal-title":"Machine Learning"},{"issue":"1","key":"4_CR4","first-page":"78","volume":"12","author":"K. Miyazaki","year":"1997","unstructured":"Miyazaki, K., Yamamura, M., Kobayashi, S.: MarcoPolo: A Reinforcement Learning System Considering TradeOff Exploitation and Exploration under Markovian Environments. Journal of Japanese Society for Artificial Intelligence\u00a012(1), 78\u201389 (1997) (in Japanese)","journal-title":"Journal of Japanese Society for Artificial Intelligence"},{"key":"4_CR5","volume-title":"The Society of Mind","author":"M. Minsky","year":"1986","unstructured":"Minsky, M.: The Society of Mind. Simon & Schuster, New York (1986)"},{"key":"4_CR6","volume-title":"Pattern-Directed Inference System","author":"J.H. Holland","year":"1978","unstructured":"Holland, J.H., Reightman, J.S.: Cognitive Systems Based on Adaptive Algorithms. In: Waterman, D.A., Hayes-Roth, F. (eds.) Pattern-Directed Inference System. Academic Press, London (1978)"},{"issue":"4","key":"4_CR7","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1145\/122344.122367","volume":"2","author":"P. Maes","year":"1991","unstructured":"Maes, P.: The Agent Network Architecture (ANA). SIGART Bulletin\u00a02(4), 115\u2013120 (1991)","journal-title":"SIGART Bulletin"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Maes, P.: Behavior-Based Artificial Intelligence. In: Proceedings of the Second International Conference on Simulation of Adaptive Behavior (From Animals to Animals 2), pp. 2\u201310. The MIT Press\/Elsevier (1993)","DOI":"10.7551\/mitpress\/3116.003.0003"},{"issue":"1","key":"4_CR9","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/JRA.1986.1087032","volume":"2","author":"R.A. Brooks","year":"1986","unstructured":"Brooks, R.A.: A Robust Layered Control System for aMobile Robot. IEEE Robotics and Automation\u00a02(1), 14\u201323 (1986)","journal-title":"IEEE Robotics and Automation"},{"key":"4_CR10","unstructured":"Firby, R.J.: An Investigation into Reactive Planning in Complex Domains. In: AAAI 1987, pp. 189\u2013208 (1987)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Kurihara, S., Onai, R.: Adaptive Selection of Reactive\/Deliberate Planning for the Dynamic Environment. In: Proceedings of the MAAMAW 1997. LNCS (LNAI), vol.\u00a01237 (1997)","DOI":"10.1007\/3-540-63077-5_29"}],"container-title":["Lecture Notes in Computer Science","Multi-Agent Systems. Theories, Languages and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/10693067_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T23:09:37Z","timestamp":1711580977000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/10693067_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998]]},"ISBN":["9783540654773","9783540492412"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/10693067_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1998]]}}}