{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T22:15:11Z","timestamp":1725747311483},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642406683"},{"type":"electronic","value":"9783642406690"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40669-0_15","type":"book-chapter","created":{"date-parts":[[2013,9,4]],"date-time":"2013-09-04T13:40:52Z","timestamp":1378302052000},"page":"163-174","source":"Crossref","is-referenced-by-count":2,"title":["An Associative State-Space Metric for Learning in Factored MDPs"],"prefix":"10.1007","author":[{"given":"Pedro","family":"Sequeira","sequence":"first","affiliation":[]},{"given":"Francisco S.","family":"Melo","sequence":"additional","affiliation":[]},{"given":"Ana","family":"Paiva","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"unstructured":"Anderson, J.: Learning and Memory: An Integrated Approach. Wiley (2000)","key":"15_CR1"},{"doi-asserted-by":"crossref","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press (1998)","key":"15_CR2","DOI":"10.1109\/TNN.1998.712192"},{"doi-asserted-by":"crossref","unstructured":"Szepesv\u00e1ri, C.: Algorithms for Reinforcement Learning. Morgan & Claypool (2010)","key":"15_CR3","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"unstructured":"Kearns, M., Koller, D.: Efficient reinforcement learning in factored MDPs. In: Proc. 1999 Int. Joint Conf. Artificial Intelligence, pp. 740\u2013747 (1999)","key":"15_CR4"},{"unstructured":"Jong, N., Stone, P.: State abstraction discovery from irrelevant state variables. In: Proc. 19th Int. Joint Conf. Artificial Intelligence, pp. 752\u2013757 (2005)","key":"15_CR5"},{"doi-asserted-by":"crossref","unstructured":"Kroon, M., Whiteson, S.: Automatic feature selection for model-based reinforcement learning in factored MDPs. In: Proc. 2009 Int. Conf. Machine Learning and Applications, pp. 324\u2013330 (2009)","key":"15_CR6","DOI":"10.1109\/ICMLA.2009.71"},{"key":"15_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-642-15420-1_7","volume-title":"Agents and Data Mining Interaction","author":"P. Sequeira","year":"2010","unstructured":"Sequeira, P., Antunes, C.: Real-time sensory pattern mining for autonomous agents. In: Cao, L., Bazzan, A.L.C., Gorodetsky, V., Mitkas, P.A., Weiss, G., Yu, P.S. (eds.) ADMI 2010. LNCS, vol.\u00a05980, pp. 71\u201383. Springer, Heidelberg (2010)"},{"unstructured":"Ribeiro, C., Szepesv\u00e1ri, C.: Q-learning combined with spreading: Convergence and results. In: Proc. Int. Conf. Intelligent and Cognitive Systems, pp. 32\u201336 (1996)","key":"15_CR8"},{"unstructured":"Ferns, N., Panangaden, P., Precup, D.: Metrics for finite Markov decision processes. In: Proc. 20th Conf. Uncertainty in Artificial Intelligence, pp. 162\u2013169 (2004)","key":"15_CR9"},{"unstructured":"Watkins, C.: Learning from delayed rewards. PhD thesis, King\u2019s College, Cambridge Univ. (1989)","key":"15_CR10"},{"key":"15_CR11","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1613\/jair.1000","volume":"19","author":"C. Guestrin","year":"2003","unstructured":"Guestrin, C., Koller, D., Parr, R., Venkataraman, S.: Efficient solution algorithms for factored MDPs. J. Artificial Intelligence Research\u00a019, 399\u2013468 (2003)","journal-title":"J. Artificial Intelligence Research"},{"unstructured":"Pavlov, I.: Conditioned reflexes: An investigation of the physiological activity of the cerebral cortex. Oxford Univ. Press (1927)","key":"15_CR12"},{"issue":"3","key":"15_CR13","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/S0149-7634(02)00007-6","volume":"26","author":"R. Cardinal","year":"2002","unstructured":"Cardinal, R., Parkinson, J., Hall, J., Everitt, B.: Emotion and motivation: The role of the amygdala, ventral striatum, and prefrontal cortex. Neuroscience and Biobehavioral Reviews\u00a026(3), 321\u2013352 (2002)","journal-title":"Neuroscience and Biobehavioral Reviews"},{"doi-asserted-by":"crossref","unstructured":"Balkenius, C., Mor\u00e9n, J.: Computational models of classical conditioning: A comparative study. In: Proc. 5th Int. Conf. Simulation of Adaptive Behavior: From Animals to Animats, vol.\u00a05, pp. 348\u2013353 (1998)","key":"15_CR14","DOI":"10.7551\/mitpress\/3119.003.0053"},{"key":"15_CR15","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1023\/B:DAMI.0000005258.31418.83","volume":"8","author":"J. Han","year":"2004","unstructured":"Han, J., Pei, J., Yin, Y., Mao, R.: Mining frequent patterns without candidate generation. Data Mining and Knowledge Disc.\u00a08, 53\u201387 (2004)","journal-title":"Data Mining and Knowledge Disc."},{"issue":"2","key":"15_CR16","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1111\/j.1469-8137.1912.tb05611.x","volume":"11","author":"P. Jaccard","year":"1912","unstructured":"Jaccard, P.: The distribution of the flora in the alpine zone. New Phytologist\u00a011(2), 37\u201350 (1912)","journal-title":"New Phytologist"},{"issue":"1","key":"15_CR17","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1023\/A:1019154432472","volume":"26","author":"A. Lipkus","year":"1999","unstructured":"Lipkus, A.: A proof of the triangle inequality for the Tanimoto distance. J. Mathematical Chemistry\u00a026(1), 263\u2013265 (1999)","journal-title":"J. Mathematical Chemistry"},{"unstructured":"Ravindran, B., Barto, A.: Approximate homomorphisms: A framework for non-exact minimization in Markov decision processes. In: Proc. 5th Int. Conf. Knowledge-Based Computer Systems (2004)","key":"15_CR18"},{"key":"15_CR19","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/S0004-3702(02)00376-4","volume":"147","author":"R. Givan","year":"2003","unstructured":"Givan, R., Dean, T., Greig, M.: Equivalence notions and model minimization in Markov Decision Processes. Artificial Intelligence\u00a0147, 163\u2013223 (2003)","journal-title":"Artificial Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Szepesv\u00e1ri, C., Smart, W.: Interpolation-based Q-learning. In: Proc. 21st Int. Conf. Machine Learning, pp. 100\u2013107 (2004)","key":"15_CR20","DOI":"10.1145\/1015330.1015445"},{"key":"15_CR21","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1023\/A:1017928328829","volume":"49","author":"D. Ormoneit","year":"2002","unstructured":"Ormoneit, D., Sen, S.: Kernel-based reinforcement learning. Machine Learning\u00a049, 161\u2013178 (2002)","journal-title":"Machine Learning"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40669-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T16:48:43Z","timestamp":1715964523000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40669-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642406683","9783642406690"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40669-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}