{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T11:27:31Z","timestamp":1746012451453,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540421856"},{"type":"electronic","value":"9783540453246"}],"license":[{"start":{"date-parts":[[2001,1,1]],"date-time":"2001-01-01T00:00:00Z","timestamp":978307200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2001,1,1]],"date-time":"2001-01-01T00:00:00Z","timestamp":978307200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2001]]},"DOI":"10.1007\/3-540-45324-5_23","type":"book-chapter","created":{"date-parts":[[2007,7,23]],"date-time":"2007-07-23T02:35:42Z","timestamp":1185158142000},"page":"249-258","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Reinforcement Learning for 3 vs. 2 Keepaway"],"prefix":"10.1007","author":[{"given":"Peter","family":"Stone","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard S.","family":"Sutton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satinder","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2001,9,20]]},"reference":[{"key":"23_CR1","volume-title":"Brains, Behavior, and Robotics","author":"J. S. Albus","year":"1981","unstructured":"J. S. Albus. Brains, Behavior, and Robotics. Byte Books, Peterborough, NH, 1981."},{"key":"23_CR2","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/3-540-64473-3_74","volume-title":"RoboCup-97: Robot Soccer World Cup","author":"T. Andou","year":"1998","unstructured":"T. Andou. Refinement of soccer agents\u2019 positions using reinforcement learning. In H. Kitano, editor, RoboCup-97: Robot Soccer World Cup I, pages 373\u2013388. Springer Verlag, Berlin, 1998."},{"key":"23_CR3","unstructured":"R. H. Crites and A. G. Barto. Improving elevator performance using reinforcement learning. In D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, editors, Advances in Neural Processing Systems 8, Cambridge, MA, 1996. MIT Press."},{"key":"23_CR4","first-page":"24","volume":"97","author":"H. Kitano","year":"1997","unstructured":"H. Kitano, M. Tambe, P. Stone, M. Veloso, S. Coradeschi, E. Osawa, H. Matsubara, I. Noda, and M. Asada. The RoboCup synthetic agent challenge 97. In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, pages 24\u201329, San Francisco, CA 1997. Morgan Kaufmann.","journal-title":"The RoboCup synthetic agent challenge"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"D. McAllester and P. Stone. Keeping the ball from cmunited-99. In P. Stone, T. Balch, and G. Kraetszchmar, editors, RoboCup-2000: Robot Soccer World Cup IV, Berlin, 2001. Springer Verlag. To appear.","DOI":"10.1007\/3-540-45324-5_35"},{"key":"23_CR6","doi-asserted-by":"publisher","first-page":"233-50","DOI":"10.1080\/088395198117848","volume":"12","author":"I. Noda","year":"1998","unstructured":"I. Noda, H. Matsubara, K. Hiraki, and I. Frank. Soccer server: A tool for research on multiagent systems. Applied Artificial Intelligence, 12:233-50, 1998.","journal-title":"Applied Artificial Intelligence"},{"key":"23_CR7","volume-title":"C4.5: Programs for Machine Learning","author":"J. R. Quinlan","year":"1993","unstructured":"J. R. Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo, CA, 1993."},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"P. Stone. Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer. MIT Press, 2000.","DOI":"10.7551\/mitpress\/4151.001.0001"},{"key":"23_CR9","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/3-540-45327-X_2","volume-title":"RoboCup-99: Robot Soccer World Cup","author":"P. Stone","year":"2000","unstructured":"P. Stone, P. Riley, and M. Veloso. The CMUnited-99 champion simulator team. In M. Veloso, E. Pagello, and H. Kitano, editors, RoboCup-99: Robot Soccer World Cup III, pages 35\u201348. Springer Verlag, Berlin, 2000."},{"key":"23_CR10","volume-title":"RoboCup-98: Robot Soccer World Cup","author":"P. Stone","year":"1999","unstructured":"P. Stone and M. Veloso. Team-partitioned, opaque-transition reinforcement learning. In M. Asada and H. Kitano, editors, RoboCup-98: Robot Soccer World Cup II. Springer Verlag, Berlin, 1999. Also in Proceedings of the Third International Conference on Autonomous Agents,1999."},{"key":"23_CR11","volume-title":"Reinforcement Learning: An Introduction","author":"R. S. Sutton","year":"1998","unstructured":"R. S. Sutton and A. G. Barto. Reinforcement Learning: An Introduction. MIT Press, Cambridge,Massachusetts, 1998."},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"R. S. Sutton and S. D. Whitehead. Online learning with random representations. In Proceedings of the Tenth International Conference on Machine Learning, pages 314-21, 1993.","DOI":"10.1016\/B978-1-55860-307-3.50047-2"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"M. Tan. Multi-agent reinforcement learning: Independent vs. cooperative agents. In Proceedings of the Tenth International Conference on Machine Learning, pages 330-37, 1993.","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"23_CR14","unstructured":"E. Uchibe. Cooperative Behavior Acquisition by Learning and Evolution in a Multi-Agent Environment for Mobile Robots. PhD thesis, Osaka University, January 1999."},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"M. Veloso, P. Stone, and M. Bowling. Anticipation as a key for collaboration in a team of agents: A case study in robotic soccer. In Proceedings of SPIE Sensor Fusion and Decentralized Control in Robotic Systems II, volume 3839, Boston, September 1999.","DOI":"10.1117\/12.360333"},{"key":"23_CR16","series-title":"PhD thesis","volume-title":"Learning from Delayed Rewards","author":"C. J. C. H. Watkins","year":"1989","unstructured":"C. J. C. H. Watkins. Learning from Delayed Rewards. PhD thesis, King\u2019s Cambridge, UK, 1989."}],"container-title":["Lecture Notes in Computer Science","RoboCup 2000: Robot Soccer World Cup IV"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-45324-5_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,23]],"date-time":"2020-10-23T05:08:20Z","timestamp":1603429700000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-45324-5_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001]]},"ISBN":["9783540421856","9783540453246"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/3-540-45324-5_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2001]]},"assertion":[{"value":"20 September 2001","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}