{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T05:10:01Z","timestamp":1743138601036,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540406662"},{"type":"electronic","value":"9783540451358"}],"license":[{"start":{"date-parts":[[2003,1,1]],"date-time":"2003-01-01T00:00:00Z","timestamp":1041379200000},"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":[[2003]]},"DOI":"10.1007\/978-3-540-45135-8_31","type":"book-chapter","created":{"date-parts":[[2010,6,22]],"date-time":"2010-06-22T21:59:26Z","timestamp":1277243966000},"page":"359-366","source":"Crossref","is-referenced-by-count":0,"title":["Direct Reward and Indirect Reward in Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Masayuki","family":"Ohta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"31_CR1","first-page":"338","volume-title":"RoboCup-98: Robot Soccer World Cup II","author":"T. Andou","year":"1998","unstructured":"Andou, T.: Andhill-98: A robocup team which reinforces positioning with observation. In: Asada, M., Kitano, H. (eds.) RoboCup-98: Robot Soccer World Cup II, pp. 338\u2013345. Springer, Heidelberg (1998)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Arai, S., Sycara, K.: Effective learning approach for planning and scheduling in multi-agent domain. In: Proceedings of the 6th International Conference on Simulation of Adaptive Behavior, pp. 507\u2013516 (2000)","DOI":"10.7551\/mitpress\/3120.003.0054"},{"key":"31_CR3","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, Cambridge University, Cambridge, England (1989)"},{"key":"31_CR4","first-page":"225","volume":"3","author":"J.J. Grefenstette","year":"1988","unstructured":"Grefenstette, J.J.: Credit assignment in rule discovery systems based on genetic algorithms. Machine Learning\u00a03, 225\u2013245 (1988)","journal-title":"Machine Learning"},{"key":"31_CR5","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Miyazaki, K., Kobayashi, S.: Rationality of reward sharing in multi-agent reinforcement learning. In: Second Pacific Rim International Workshop on Multi-Agents, pp. 111\u2013125 (1999)","DOI":"10.1007\/3-540-46693-2_9"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Noda, I., Matsubara, H., Hiraki, K., Frank, I.: Soccer server: A tool for research on multiagent systems. In: Applied Artificial Intelligence, vol.\u00a012, pp. 233\u2013250 (1998)","DOI":"10.1080\/088395198117848"},{"key":"31_CR8","unstructured":"Sen, S., Sekaran, M., Hale, J.: Proceedings of the 12th national conference on artificial intelligence. Learning to Coordinate without Sharing Information, 426\u2013431 (1994)"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Stone, P., McAllester, D.: An Architecture for Action Selection in Robotic Soccer. In: Proceedings of the Fifth International Conference on Autonomous Agents (2001)","DOI":"10.1145\/375735.376320"},{"key":"31_CR10","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)"}],"container-title":["Lecture Notes in Computer Science","RoboCup 2002: Robot Soccer World Cup VI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-45135-8_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T19:30:29Z","timestamp":1711567829000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-45135-8_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540406662","9783540451358"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-45135-8_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2003]]}}}