{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:43:03Z","timestamp":1743021783115,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540688464"},{"type":"electronic","value":"9783540688471"}],"license":[{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008]]},"DOI":"10.1007\/978-3-540-68847-1_9","type":"book-chapter","created":{"date-parts":[[2008,7,17]],"date-time":"2008-07-17T08:26:35Z","timestamp":1216283195000},"page":"101-112","source":"Crossref","is-referenced-by-count":1,"title":["Cooperative\/Competitive Behavior Acquisition Based on State Value Estimation of Others"],"prefix":"10.1007","author":[{"given":"Kentaro","family":"Noma","sequence":"first","affiliation":[]},{"given":"Yasutake","family":"Takahashi","sequence":"additional","affiliation":[]},{"given":"Minoru","family":"Asada","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"9_CR1","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-3184-5","volume-title":"ROBOT LEARNING","author":"J.H. Connell","year":"1993","unstructured":"Connell, J.H., Mahadevan, S.: ROBOT LEARNING. Kluwer Academic Publishers, Dordrecht (1993)"},{"key":"9_CR2","unstructured":"Doya, K., Samejima, K., Katagiri, K.i., Kawato, M.: Multiple model-based reinforcement learning. Technical report, Kawato Dynamic Brain Project Technical Report, KDB-TR-08, Japan Science and Technology Corporation (June 2000)"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Elfwing, S., Uchibe, E., Doya, K., Chirstensen, H.I.: Multi-agent reinforcement learning: Using macro actions to learn a mating task. In: Proceedings of 2004 IEEE\/RSJ International Conference on Intelligent Robots and Systems, vol.\u00a04, pp. 3164\u20133169 (2004)","DOI":"10.1109\/IROS.2004.1389904"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Ikenoue, S., Asada, M., Hosoda, K.: Cooperative behavior acquisition by asynchronous policy renewal that enables simultaneous learning in multiagent environment. In: Proceedings of the 2002 IEEE\/RSJ Intl. Conference on Intelligent Robots and Systems, pp. 2728\u20132734 (2002)","DOI":"10.1109\/IRDS.2002.1041682"},{"key":"9_CR5","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"R. Jacobs","year":"1991","unstructured":"Jacobs, R., Jordan, M., Nowlan, S., Hinton, G.: Adaptive mixture of local experts. Neural Computation\u00a03, 79\u201387 (1991)","journal-title":"Neural Computation"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Kalyanakrishnan, S., Liu, Y., Stone, P.: Half field offense in robocup soccer: A multiagent reinforcement learning case study. In: Proceedings CD RoboCup (2006)","DOI":"10.1007\/978-3-540-74024-7_7"},{"key":"9_CR7","first-page":"323","volume":"8","author":"S.P. Singh","year":"1992","unstructured":"Singh, S.P.: Transfer of learning by composing solutions of elemental sequential tasks. Machine Learning\u00a08, 323\u2013339 (1992)","journal-title":"Machine Learning"},{"key":"9_CR8","first-page":"2201","volume":"13","author":"P. Stone","year":"2003","unstructured":"Stone, P., Sutton, R.S., Kuhlmann, G.: Scaling reinforcement learning toward robocup soccer. Journal of Machine Learing Research\u00a013, 2201\u20132220 (2003)","journal-title":"Journal of Machine Learing Research"},{"key":"9_CR9","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Takahashi, Y., Edazawa, K., Asada, M.: Multi-module learning system for behavior acquisition in multi-agent environment. In: Proceedings of 2002 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. CD\u2013ROM 927\u2013931 (October 2002)","DOI":"10.1109\/IRDS.2002.1041509"},{"key":"9_CR11","unstructured":"Takahashi, Y., Kawamata, T., Asada, M.: Learning utility for behavior acquisition and intention inference of other agent. In: Proceedings of the 2006 IEEE\/RSJ IROS 2006 Workshop on Multi-objective Robotics, pp. 25\u201331 (2006)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Whitehead, S., Karlsson, J., Tenenberg, J.: Learning multiple goal behavior via task decomposition and dynamic policy merging. In: Connell, J.H., Mahadevan, S. (eds.) ROBOT LEARNING, ch.3, pp. 45\u201378. Kluwer Academic Publishers (1993)","DOI":"10.1007\/978-1-4615-3184-5_3"}],"container-title":["Lecture Notes in Computer Science","RoboCup 2007: Robot Soccer World Cup XI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-68847-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T01:48:43Z","timestamp":1738288123000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-68847-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540688464","9783540688471"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-68847-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}