{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:57:00Z","timestamp":1725559020126},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642142734"},{"type":"electronic","value":"9783642142741"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-14274-1_8","type":"book-chapter","created":{"date-parts":[[2010,7,9]],"date-time":"2010-07-09T05:32:53Z","timestamp":1278653573000},"page":"81-95","source":"Crossref","is-referenced-by-count":1,"title":["Reducing the Memory Footprint of Temporal Difference Learning over Finitely Many States by Using Case-Based Generalization"],"prefix":"10.1007","author":[{"given":"Matt","family":"Dilts","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H\u00e9ctor","family":"Mu\u00f1oz-Avila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","first-page":"1041","volume-title":"Proceedings of the 20th Int. Joint Conf. on AI (IJCAI 2007)","author":"M. Sharma","year":"2007","unstructured":"Sharma, M., Holmes, M., Santamaria, J.C., Irani Jr., A., Ram, A.: Transfer learning in real-time strategy games using hybrid CBR\/RL. In: Proceedings of the 20th Int. Joint Conf. on AI (IJCAI 2007), pp. 1041\u20131046. AAAI Press, Menlo Park (2007)"},{"key":"8_CR2","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1007\/978-3-540-25940-4_73","volume-title":"RoboCup 2003: Robot Soccer World Cup VII","author":"A. Karol","year":"2004","unstructured":"Karol, A., Nebel, B., Stanton, C., Williams, M.A.: Case based game play in the robocup four-legged league part I the theoretical model. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds.) RoboCup 2003. LNCS (LNAI), vol.\u00a03020, pp. 739\u2013747. Springer, Heidelberg (2004)"},{"key":"8_CR3","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-540-85502-6_4","volume-title":"Advances in Case-Based Reasoning","author":"B. Auslander","year":"2008","unstructured":"Auslander, B., Lee-Urban, S., Hogg, C., Munoz-Avila, H.: Recognizing The Enemy: Combining Reinforcement Learning with Strategy Selection using Case-Based Reasoning. In: Althoff, K.-D., Bergmann, R., Minor, M., Hanft, A. (eds.) ECCBR 2008. LNCS (LNAI), vol.\u00a05239, pp. 59\u201373. Springer, Heidelberg (2008)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Juell, P., Paulson, P.: Using reinforcement learning for similarity assessment in case-based systems. IEEE Intelligent Systems, 60\u201367 (2003)","DOI":"10.1109\/MIS.2003.1217629"},{"key":"8_CR5","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/11536406_1","volume-title":"Case-Based Reasoning Research and Development","author":"D. Bridge","year":"2005","unstructured":"Bridge, D.: The virtue of reward: Performance, reinforcement and discovery in case-based reasoning. In: Mu\u00f1oz-\u00c1vila, H., Ricci, F. (eds.) ICCBR 2005. LNCS (LNAI), vol.\u00a03620, p. 1. Springer, Heidelberg (2005)"},{"key":"8_CR6","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/11536406_18","volume-title":"Case-Based Reasoning Research and Development","author":"T. Gabel","year":"2005","unstructured":"Gabel, T., Riedmiller, M.A.: CBR for state value function approximation in reinforcement learning. In: Mu\u00f1oz-\u00c1vila, H., Ricci, F. (eds.) ICCBR 2005. LNCS (LNAI), vol.\u00a03620, pp. 206\u2013221. Springer, Heidelberg (2005)"},{"key":"8_CR7","series-title":"LNAI","first-page":"75","volume-title":"ICCBR 2009","author":"R. Bianchi","year":"2009","unstructured":"Bianchi, R., Ros, R., Lopez de Mantaras, R.: Improving Reinforcement Learning by using Case-Based Heuristics. In: McGinty, L., Wilson, D.C. (eds.) ICCBR 2009. LNCS (LNAI), vol.\u00a05650, pp. 75\u201389. Springer, Heidelberg (2009)"},{"key":"8_CR8","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":"8_CR9","doi-asserted-by":"crossref","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning, 9\u201344 (1988)","DOI":"10.1007\/BF00115009"},{"issue":"3","key":"8_CR10","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G. Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal difference learning and TD-Gammon. Communications of the ACM\u00a038(3), 58\u201368 (1995)","journal-title":"Communications of the ACM"},{"key":"8_CR11","unstructured":"http:\/\/en.wikipedia.org\/wiki\/Descent:_Journeys_in_the_Dark (Last checked: February 2010)"},{"key":"8_CR12","first-page":"1801","volume-title":"Proceedings of the Innovative Applications of Artificial Intelligence Conference","author":"M. Vasta","year":"2007","unstructured":"Vasta, M., Lee-Urban, S., Munoz-Avila, H.: RETALIATE: Learning Winning Policies in First-Person Shooter Games. In: Proceedings of the Innovative Applications of Artificial Intelligence Conference, pp. 1801\u20131806. AAAI Press, Menlo Park (2007)"},{"key":"8_CR13","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1007\/3-540-45327-X_24","volume-title":"RoboCup-99: Robot Soccer World Cup III","author":"F. Fern\u00e1ndez","year":"2000","unstructured":"Fern\u00e1ndez, F., Borrajo, D.: VQQL. Applying vector quantization to reinforcement learning. In: Veloso, M.M., Pagello, E., Kitano, H. (eds.) RoboCup 1999. LNCS (LNAI), vol.\u00a01856, pp. 292\u2013303. Springer, Heidelberg (2000)"},{"key":"8_CR14","first-page":"371","volume-title":"Proceedings of the Int. Conf. on CBR","author":"E. Auriol","year":"1995","unstructured":"Auriol, E., Wess, S., Manago, M., Althoff, K.-D., Traph\u00f6ner, R.: INRECA: A Seamlessly Integrated System Based on Induction and Case-Based Reasoning. In: Proceedings of the Int. Conf. on CBR, pp. 371\u2013380. Springer, Heidelberg (1995)"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Ram, A., Santamaria, J.C.: Continuous case-based reasoning. Artificial Intelligence, 25\u201377 (1997)","DOI":"10.1016\/S0004-3702(96)00037-9"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Santamaria, J.C., Sutton, R.S., Ram, A.: Experiments with Reinforcement Learning in Problems with Continuous State and Action Spaces. Adaptive Behavior, 163\u2013217 (1998)","DOI":"10.1177\/105971239700600201"},{"key":"8_CR17","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1007\/978-3-540-74141-1_24","volume-title":"Case-Based Reasoning Research and Development","author":"T. Gabel","year":"2007","unstructured":"Gabel, T., Riedmiller, M.: An Analysis of Case-Based Value Function Approximation by Approximating State Transition Graphs. In: Weber, R.O., Richter, M.M. (eds.) ICCBR 2007. LNCS (LNAI), vol.\u00a04626, pp. 344\u2013358. Springer, Heidelberg (2007)"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"McCallum, R.A.: Instance-Based State Identification for Reinforcement Learning. In: Advances in Neural Information Processing Systems, NIPS 7 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50055-4"},{"key":"8_CR19","first-page":"257","volume-title":"Proceedings of the Twenty-Second International FLAIRS Conference","author":"M. Molineaux","year":"2009","unstructured":"Molineaux, M., Aha, D.W., Sukthankar, G.: Beating the defense: Using plan recognition to inform learning agents. In: Proceedings of the Twenty-Second International FLAIRS Conference, pp. 257\u2013262. AAAI Press, Menlo Park (2009)"},{"key":"8_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1007\/978-3-642-02998-1_10","volume-title":"ICCBR 2009","author":"L. Cummins","year":"2009","unstructured":"Cummins, L., Bridge, D.: Maintenance by a Committee of Experts: The MACE Approach to Case-Base Maintenance. In: McGinty, L., Wilson, D.C. (eds.) ICCBR 2009. LNCS, vol.\u00a05650, pp. 120\u2013134. Springer, Heidelberg (2009)"},{"key":"8_CR21","first-page":"567","volume-title":"AI Game Programming Wisdom","author":"R. Evans","year":"2002","unstructured":"Evans, R.: Varieties of Learning. In: AI Game Programming Wisdom, pp. 567\u2013578. Charles River Media, Hingham (2002)"},{"key":"8_CR22","first-page":"217","volume-title":"AI Game Programming Wisdom","author":"J. Orkin","year":"2003","unstructured":"Orkin, J.: Applying Goal-Oriented Action Planning to Games. In: AI Game Programming Wisdom, vol.\u00a02, pp. 217\u2013228. Charles River Media, Hingham (2003)"}],"container-title":["Lecture Notes in Computer Science","Case-Based Reasoning. Research and Development"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-14274-1_8.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T02:50:16Z","timestamp":1606186216000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-14274-1_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642142734","9783642142741"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-14274-1_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}