{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T22:50:26Z","timestamp":1725490226481},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540745648"},{"type":"electronic","value":"9783540745655"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-74565-5_18","type":"book-chapter","created":{"date-parts":[[2007,8,25]],"date-time":"2007-08-25T06:01:04Z","timestamp":1188021664000},"page":"220-234","source":"Crossref","is-referenced-by-count":9,"title":["Making a Robot Learn to Play Soccer Using Reward and Punishment"],"prefix":"10.1007","author":[{"given":"Heiko","family":"M\u00fcller","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Lauer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Hafner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sascha","family":"Lange","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Artur","family":"Merke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Riedmiller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"18_CR1","first-page":"146","volume-title":"Proc. of IEEE Int. Conf. on Robotics and Automation","author":"M. Asada","year":"1995","unstructured":"Asada, M., Noda, S., Tawaratsumida, S., Hosoda, K.: Vision-based reinforcement learning for purposive behavior acquisition. In: Proc. of IEEE Int. Conf. on Robotics and Automation, pp. 146\u2013153. IEEE Computer Society Press, Los Alamitos (1995)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Baird, L.C.: Residual algorithms: Reinforcement learning with function approximation. In: Proceedings of the 12th International Conference on Machine Learning, pp. 30\u201337 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"18_CR3","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1007\/978-3-540-25940-4_70","volume-title":"RoboCup 2003: Robot Soccer World Cup VII","author":"S. Behnke","year":"2004","unstructured":"Behnke, S., Egorova, A., Gloye, A., Rojas, R., Simon, M.: Predicting away robot control latency. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds.) RoboCup 2003. LNCS (LNAI), vol.\u00a03020, pp. 712\u2013719. Springer, Heidelberg (2004)"},{"key":"18_CR4","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Athena Scientific (1996)"},{"key":"18_CR5","unstructured":"Gabel, T., Hafner, R., Lange, S., Lauer, M., Riedmiller, M.: Bridging the gap: Learning in the robocup simulation and midsize league. In: Controlo 2006. Proc. 7th Portuguese Conference on Automatic Control (2006)"},{"issue":"2","key":"18_CR6","first-page":"18","volume":"20","author":"T. Gabel","year":"2006","unstructured":"Gabel, T., Riedmiller, M.: Learning a partial behavior for a competitive robotic soccer agent. K\u00fcnstliche Intelligenz\u00a020(2), 18\u201323 (2006)","journal-title":"K\u00fcnstliche Intelligenz"},{"key":"18_CR7","series-title":"LNCS(LNAI)","volume-title":"RoboCup-2006","author":"R. Hafner","year":"2006","unstructured":"Hafner, R., Lange, S., Lauer, M., Riedmiller, M.: Brainstormers Tribots team description. In: Lakemeyer, G., Sklar, E., Sorrenti, D.G., Takahashi, T. (eds.) RoboCup-2006. LNCS(LNAI), vol.\u00a04434, Springer, Heidelberg (2006)"},{"key":"18_CR8","volume-title":"Dynamic programming and Markov processes","author":"R.A. Howard","year":"1960","unstructured":"Howard, R.A.: Dynamic programming and Markov processes. MIT Press, Cambridge (1960)"},{"issue":"1","key":"18_CR9","first-page":"73","volume":"18","author":"H. Kitano","year":"1997","unstructured":"Kitano, H., Asada, M., Kuniyoshi, Y., Noda, I., Osawa, E., Matsubara, H.: RoboCup: A challenge problem for AI. AI Magazine\u00a018(1), 73\u201385 (1997)","journal-title":"AI Magazine"},{"key":"18_CR10","series-title":"LNCS(LNAI)","volume-title":"RoboCup-2006","author":"M. Lauer","year":"2006","unstructured":"Lauer, M.: Ego-motion estimation and collision detection for omnidirectional robots. In: Lakemeyer, G., Sklar, E., Sorrenti, D.G., Takahashi, T. (eds.) RoboCup-2006. LNCS(LNAI), vol.\u00a04434, Springer, Heidelberg (2006)"},{"issue":"1","key":"18_CR11","first-page":"11","volume":"20","author":"M. Lauer","year":"2006","unstructured":"Lauer, M., Lange, S., Riedmiller, M.: Motion estimation of moving objects for autonomous mobile robots. K\u00fcnstliche Intelligenz\u00a020(1), 11\u201317 (2006)","journal-title":"K\u00fcnstliche Intelligenz"},{"key":"18_CR12","unstructured":"Merke, A., Schoknecht, R.: A necessary condition of convergence for reinforcement learning with function approximation. In: Proceedings of the 19th International Conference on Machine Learning, pp. 411\u2013418 (2002)"},{"key":"18_CR13","unstructured":"Munos, R., Moore, A.: Variable resolution discretization for high-accuracy solutions of optimal control problems. In: International Joint Conferenece on Artificial Intelligence, pp. 1348\u20131355 (1999)"},{"key":"18_CR14","first-page":"1036","volume":"10","author":"S. Pareigis","year":"1997","unstructured":"Pareigis, S.: Adaptive choice of grid and time in reinforcement learning. Advances inNeural Information Processing Systems\u00a010, 1036\u20131042 (1997)","journal-title":"Advances inNeural Information Processing Systems"},{"key":"18_CR15","unstructured":"Schoknecht, R., Merke, A.: Convergent combinations of reinforcement learning with linear function approximation. Advances in Neural Information Processing Systems 15 (2003)"},{"key":"18_CR16","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":"18_CR17","unstructured":"Suzuki, S., Kato, T., Asada, M., Hosoda, K.: Behavior learning for a mobile robot with omnidirectional vision enhanced by an active zoom mechanism. In: IAS-5. Proc. of Intelligent Autonomous System 5, pp. 242\u2013249 (1998)"},{"key":"18_CR18","unstructured":"Tsitsiklis, J.N., Van Roy, B.: Analysis of temporal-diffference learning with function approximation. In: Advances in Neural Information Processing Systems 1996, pp. 1075\u20131081 (1996)"},{"key":"18_CR19","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49240-2_5","volume-title":"Learning Robots","author":"E. Uchibe","year":"1998","unstructured":"Uchibe, E., Asada, M., Hosoda, K.: Behavior learning for a mobile robot with omnidirectional vision enhanced by an active zoom mechanism. In: Birk, A., Demiris, J. (eds.) Learning Robots. LNCS (LNAI), vol.\u00a01545, Springer, Heidelberg (1998)"},{"key":"18_CR20","first-page":"279","volume":"8","author":"C.J.C.H. Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"}],"container-title":["Lecture Notes in Computer Science","KI 2007: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-74565-5_18.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T10:24:52Z","timestamp":1619519092000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-74565-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540745648","9783540745655"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-74565-5_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}