{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T20:26:05Z","timestamp":1767903965291,"version":"3.49.0"},"reference-count":16,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2001,5,1]],"date-time":"2001-05-01T00:00:00Z","timestamp":988675200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotics and Autonomous Systems"],"published-print":{"date-parts":[[2001,5]]},"DOI":"10.1016\/s0921-8890(01)00114-2","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T10:48:12Z","timestamp":1027594092000},"page":"109-122","source":"Crossref","is-referenced-by-count":78,"title":["Modular Q-learning based multi-agent cooperation for robot soccer"],"prefix":"10.1016","volume":"35","author":[{"given":"Kui-Hong","family":"Park","sequence":"first","affiliation":[]},{"given":"Yong-Jae","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Jong-Hwan","family":"Kim","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0921-8890(01)00114-2_BIB1","doi-asserted-by":"crossref","unstructured":"R.S. Sutton, A.G. Barto, Reinforcement Learning: An Introduction, Bradford Books\/MIT Press, Cambridge, MA, 1998.","DOI":"10.1109\/TNN.1998.712192"},{"key":"10.1016\/S0921-8890(01)00114-2_BIB2","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine Learning"},{"issue":"2","key":"10.1016\/S0921-8890(01)00114-2_BIB3","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1177\/105971239300200204","article-title":"Collective robotics: From social insects to robot","volume":"2","author":"Kube","year":"1993","journal-title":"Adaptive Behavior"},{"key":"10.1016\/S0921-8890(01)00114-2_BIB4","doi-asserted-by":"crossref","unstructured":"G. Campion, G. Bastin, D\u2019Andr\u00e9a-Novel, Structural properties and classification of kinematic and dynamic models of wheeled mobile robots, IEEE Transactions on Robotics and Automation 12 (1) (1996) 47\u201362.","DOI":"10.1109\/70.481750"},{"key":"10.1016\/S0921-8890(01)00114-2_BIB5","doi-asserted-by":"crossref","unstructured":"L.P. Kaelbling, M.L. Littman, A.W. Moore, Reinforcement learning: A survey, Journal of Artificial Intelligence Research 4 (1996) 237\u2013285.","DOI":"10.1613\/jair.301"},{"key":"10.1016\/S0921-8890(01)00114-2_BIB6","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/0303-2647(95)01551-5","article-title":"Multiagent reinforcement learning in the Iterated Prisoner\u2019s Dilemma","volume":"37","author":"Sandholm","year":"1996","journal-title":"Biosystems"},{"issue":"2","key":"10.1016\/S0921-8890(01)00114-2_BIB7","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/S0921-8890(97)00023-7","article-title":"Designing distributed control architecture for cooperative multi-agent system and its real-time application to soccer robot","volume":"21","author":"Shim","year":"1997","journal-title":"Robotics and Autonomous Systems"},{"issue":"10","key":"10.1016\/S0921-8890(01)00114-2_BIB8","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1002\/(SICI)1098-111X(199710)12:10<695::AID-INT1>3.0.CO;2-T","article-title":"Training and delay reinforcements in Q-learning agents","volume":"12","author":"Caironi","year":"1997","journal-title":"International Journal of Intelligent Systems"},{"issue":"2","key":"10.1016\/S0921-8890(01)00114-2_BIB9","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1109\/70.681242","article-title":"Alliance: An architecture for fault tolerant multirobot cooperation","volume":"14","author":"Parker","year":"1998","journal-title":"IEEE Transactions on Robotics and Automation"},{"key":"10.1016\/S0921-8890(01)00114-2_BIB10","doi-asserted-by":"crossref","unstructured":"J.-H. Kim, H.-S. Shim, H.-S. Kim, M.-J. Jung, I.-H. Choi, K.-O. Kim, A cooperative multi-agent system and its real time application to robot soccer, in: Proceedings of the IEEE International Conference on Robotics and Automation, Minneapolis, MN, 1996, pp. 638\u2013643.","DOI":"10.1109\/ROBOT.1997.620108"},{"key":"10.1016\/S0921-8890(01)00114-2_BIB11","unstructured":"C. Boutilier, Planning, learning and coordination in multiagent decision processes, in: Proceedings of the Sixth Conference on Theoretical Aspects of Rationality and Knowledge, Netherlands, 1996."},{"key":"10.1016\/S0921-8890(01)00114-2_BIB12","unstructured":"S.H. Lee, J. Bautista, Motion control for micro-robots playing soccer games, in: Proceedings of the IEEE International Conference on Robotics and Automation, Leuven, Belgium, 1998, pp. 2599\u20132604."},{"key":"10.1016\/S0921-8890(01)00114-2_BIB13","unstructured":"J.-H. Kim, K.-C. Kim, D.-H. Kim, Y.-J. Kim, P. Vadakkepat, Path planning and role selection mechanism for soccer robots, in: Proceedings of the IEEE International Conference on Robotics and Automation, Leuven, Belgium, 1998, pp. 3216\u20133221."},{"key":"10.1016\/S0921-8890(01)00114-2_BIB14","doi-asserted-by":"crossref","unstructured":"Y.-J. Kim, D.-H. Kim, J.-H. Kim, Evolutionary programming-based vector field method for fast mobile robot navigation, in: Proceedings of the Second Asia\u2013Pacific Conference on Simulations, Evolutions and Learning, 1998.","DOI":"10.1007\/3-540-48873-1_21"},{"key":"10.1016\/S0921-8890(01)00114-2_BIB15","unstructured":"N. Ono, K. Fukumoto, Multi-agent reinforcement learning: A modular approach, in: Proceedings of the Second International Conference on Multi-agent Systems, AAAI Press, 1996, pp. 252\u2013258."},{"key":"10.1016\/S0921-8890(01)00114-2_BIB16","unstructured":"G.A. Rummery, Problem solving with reinforcement learning, Ph.D. Thesis, Cambridge University, Cambridge, UK, 1995."}],"container-title":["Robotics and Autonomous Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889001001142?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889001001142?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:16:09Z","timestamp":1733246169000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0921889001001142"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,5]]},"references-count":16,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2001,5]]}},"alternative-id":["S0921889001001142"],"URL":"https:\/\/doi.org\/10.1016\/s0921-8890(01)00114-2","relation":{},"ISSN":["0921-8890"],"issn-type":[{"value":"0921-8890","type":"print"}],"subject":[],"published":{"date-parts":[[2001,5]]}}}