{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:34:01Z","timestamp":1743032041875,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540740230"},{"type":"electronic","value":"9783540740247"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"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":[[2007]]},"DOI":"10.1007\/978-3-540-74024-7_5","type":"book-chapter","created":{"date-parts":[[2007,8,31]],"date-time":"2007-08-31T06:46:08Z","timestamp":1188542768000},"page":"47-58","source":"Crossref","is-referenced-by-count":10,"title":["Imitative Reinforcement Learning for Soccer Playing Robots"],"prefix":"10.1007","author":[{"given":"Tobias","family":"Latzke","sequence":"first","affiliation":[]},{"given":"Sven","family":"Behnke","sequence":"additional","affiliation":[]},{"given":"Maren","family":"Bennewitz","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"5_CR1","volume-title":"Artificial Intelligence: A Modern Approach","author":"S. Russell","year":"2003","unstructured":"Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Prentice-Hall, Englewood Cliffs, NJ (2003)","edition":"2"},{"key":"5_CR2","first-page":"259","volume-title":"Proc. of Conference on Advances in Neural Information Processing Systems","author":"G. Tesauro","year":"1992","unstructured":"Tesauro, G.: Practical issues in temporal difference learning. In: Proc. of Conference on Advances in Neural Information Processing Systems, vol.\u00a04, pp. 259\u2013266. Morgan Kaufmann Publishers, San Francisco (1992)"},{"key":"5_CR3","series-title":"Lecture Notes in Artificial Intelligence","volume-title":"RoboCup 2003: Robot Soccer World Cup VII","author":"M. Riedmiller","year":"2004","unstructured":"Riedmiller, M., Merke, A., Nowak, W., Nickschas, M., Withopf, D.: Brainstormers 2003 - team description. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds.) RoboCup 2003. LNCS (LNAI), vol.\u00a03020, Springer, Heidelberg (2004)"},{"unstructured":"Asada, M., Ogino, M., Matsuyama, S., Ooga, J.: Imitation learning based on visuo-somatic mapping. In: ISER. Proc. of International Symposium on Experimental Robotics (2004)","key":"5_CR4"},{"issue":"2-3","key":"5_CR5","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.robot.2004.03.010","volume":"47","author":"D.C. Bentivegna","year":"2004","unstructured":"Bentivegna, D.C., Atkeson, C.G., Cheng, G.: Learning tasks from observation and practice. Journal of Robotics & Autonomous Systems\u00a047(2-3), 163\u2013169 (2004)","journal-title":"Journal of Robotics & Autonomous Systems"},{"issue":"2-3","key":"5_CR6","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.robot.2004.03.005","volume":"47","author":"R. Dillmann","year":"2004","unstructured":"Dillmann, R.: Teaching and learning of robot tasks via observation of human performance. Journal of Robotics & Autonomous Systems\u00a047(2-3), 109\u2013116 (2004)","journal-title":"Journal of Robotics & Autonomous Systems"},{"unstructured":"Ito, M., Tani, J.: Joint attention between a humanoid robot and users in imitation game. In: ICDL. Proc.\u00a0of the Int.\u00a0Conf.\u00a0on Development and Learning (2004)","key":"5_CR7"},{"key":"5_CR8","volume-title":"Imitation in Animals and Artifacts","author":"M.J. Mataric","year":"2002","unstructured":"Mataric, M.J.: Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In: Dautenhahn, K., Nehaniv, C. (eds.) Imitation in Animals and Artifacts, MIT Press, Cambridge (2002)"},{"unstructured":"Schaal, S.: Learning from demonstration. In: Proc.\u00a0of the Conf.\u00a0on Neural Information Processing Systems (NIPS) (1997)","key":"5_CR9"},{"key":"5_CR10","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning\u00a03, 9\u201344 (1988)","journal-title":"Machine Learning"},{"unstructured":"Hinton, G.E.: Distributed representations. Technical Report CMU-CS-84-157, Carnegie-Mellon University, Computer Science Department, Pittsburgh, PA (1984)","key":"5_CR11"},{"doi-asserted-by":"crossref","unstructured":"Peng, J., Williams, R.J.: Incremental multi-step Q-learning. In: Proceedings of the 11th International Conference on Machine Learning, pp. 226\u2013232 (1994)","key":"5_CR12","DOI":"10.1016\/B978-1-55860-335-6.50035-0"},{"key":"5_CR13","first-page":"703","volume-title":"Proc. of 7th Conference on Advances in Neural Information Processing Systems","author":"T. Jaakkola","year":"1994","unstructured":"Jaakkola, T., Jordan, M.I., Singh, S.P.: Convergence of stochastic iterative dynamic programming algorithms. In: Cowan, J.D., Tesauro, G., Alspector, J. (eds.) Proc. of 7th Conference on Advances in Neural Information Processing Systems, pp. 703\u2013710. Morgan Kaufmann, San Francisco (1994)"},{"key":"5_CR14","series-title":"Lecture Notes in Artificial Intelligence","volume-title":"RoboCup 2005: Robot Soccer World Cup IX","author":"S. Behnke","year":"2006","unstructured":"Behnke, S., M\u00fcller, J., Schreiber, M.: Playing soccer with RoboSapien. In: Bredenfeld, A., Jacoff, A., Noda, I., Takahashi, Y. (eds.) RoboCup 2005. LNCS (LNAI), vol.\u00a04020, Springer, Heidelberg (2006)"},{"key":"5_CR15","first-page":"271","volume-title":"International Joint Conference on Artificial Intelligence","author":"F.A. Aloul","year":"2003","unstructured":"Aloul, F.A., Markov, I.L., Sakallah, K.A.: Efficient symmetry breaking for Boolean satisfiability. In: International Joint Conference on Artificial Intelligence, vol.\u00a03, pp. 271\u2013282. AAAI, Stanford (2003)"},{"doi-asserted-by":"crossref","unstructured":"Withopf, D., Riedmiller, M.: Effective methods for reinforcement learning in large multi-agent domains. Information Technology Journal\u00a047(5) (2005)","key":"5_CR16","DOI":"10.1524\/itit.2005.47.5_2005.241"},{"key":"5_CR17","doi-asserted-by":"crossref","first-page":"315","DOI":"10.7551\/mitpress\/3118.003.0039","volume-title":"From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior","author":"A. McCallum","year":"1996","unstructured":"McCallum, A.: Learning to use selective attention and short-term memory in sequential tasks. In: Maes, P., Matari, M., Meyer, J.A., Pollack, J., Wilson, S. (eds.) From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, Berlin, pp. 315\u2013324. MIT Press, Cambridge (1996)"},{"issue":"2","key":"5_CR18","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1177\/105971239700600202","volume":"6","author":"M. Wiering","year":"1997","unstructured":"Wiering, M., Schmidhuber, J.: HQ-learning. Adaptive Behavior\u00a06(2), 219\u2013246 (1997)","journal-title":"Adaptive Behavior"},{"key":"5_CR19","first-page":"503","volume":"6","author":"D. Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. Journal of Machine Learning Research\u00a06, 503\u2013556 (2005)","journal-title":"Journal of Machine Learning Research"},{"unstructured":"Storck, J., Hochreiter, J., Schmidhuber, J.: Reinforcement driven information acquisition in non-deterministic environments. In: Proc. of ICANN 1995. vol.\u00a02., Paris, pp. 159\u2013164 (1995)","key":"5_CR20"},{"unstructured":"Maclin, R., Shavlik, J.W.: Incorporating advice into agents that learn from reinforcements. In: Proc. of 12th National Conference on Artificial Intelligence, pp. 694\u2013699 (1994)","key":"5_CR21"},{"unstructured":"Demiris, J., Hayes, G.: A robot controller using learning by imitation. In: Proceedings of the 2nd International Symposium on Intelligent Robotic Systems, Grenoble, France (1994)","key":"5_CR22"},{"doi-asserted-by":"crossref","unstructured":"Riedmiller, M., Merke, A., Meier, D., Hoffmann, A., Sinner, A., Thate, O., Ehrmann, R.: Karlsruhe Brainstormers \u2014 A reinforcement learning approach to robotic soccer. Lecture Notes in Computer Science (2001)","key":"5_CR23","DOI":"10.1007\/3-540-45324-5_40"},{"unstructured":"Dietl, M.: Reinforcement-Lernen im Roboterfu\u00dfball. Diplomarbeit (in German), Albert-Ludwigs-Universit\u00e4t Freiburg (2002)","key":"5_CR24"}],"container-title":["Lecture Notes in Computer Science","RoboCup 2006: Robot Soccer World Cup X"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-74024-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T17:55:17Z","timestamp":1708192517000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-74024-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540740230","9783540740247"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-74024-7_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2007]]}}}