{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:53:46Z","timestamp":1725684826145},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642299452"},{"type":"electronic","value":"9783642299469"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-29946-9_9","type":"book-chapter","created":{"date-parts":[[2012,5,18]],"date-time":"2012-05-18T17:01:49Z","timestamp":1337360509000},"page":"54-65","source":"Crossref","is-referenced-by-count":0,"title":["Handling Ambiguous Effects in Action Learning"],"prefix":"10.1007","author":[{"given":"Boris","family":"Lesner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruno","family":"Zanuttini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"9_CR1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.575","volume":"11","author":"C. Boutilier","year":"1999","unstructured":"Boutilier, C., Dean, T., Hanks, S.: Decision-theoretic planning: Structural assumptions and computational leverage. J. Artificial Intelligence Research\u00a011, 1\u201394 (1999)","journal-title":"J. Artificial Intelligence Research"},{"key":"9_CR2","first-page":"213","volume":"3","author":"R.I. Brafman","year":"2002","unstructured":"Brafman, R.I., Tennenholtz, M.: R-max: A general polynomial time algorithm for near-optimal reinforcement learning. J. Machine Learning Research\u00a03, 213\u2013231 (2002)","journal-title":"J. Machine Learning Research"},{"key":"9_CR3","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/S0004-3702(96)00023-9","volume":"89","author":"R. Dearden","year":"1997","unstructured":"Dearden, R., Boutilier, C.: Abstraction and approximate decision-theoretic planning. Artificial Intelligence\u00a089, 219\u2013283 (1997)","journal-title":"Artificial Intelligence"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Degris, T., Sigaud, O., Wuillemin, P.-H.: Learning the structure of factored Markov Decision Processes in reinforcement learning problems. In: Proc. International Conference on Machine Learning (ICML\u00a02006), pp. 257\u2013264. ACM (2006)","DOI":"10.1145\/1143844.1143877"},{"key":"9_CR5","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1007694015589","volume":"43","author":"S. D\u017eeroski","year":"2001","unstructured":"D\u017eeroski, S., De Raedt, L., Driessens, K.: Relational reinforcement learning. Machine Learning\u00a043, 7\u201352 (2001)","journal-title":"Machine Learning"},{"key":"9_CR6","unstructured":"Kearns, M., Koller, D.: Efficient reinforcement learning in factored MDPs. In: Proc. 16th International Joint Conference on Artificial Intelligence (IJCAI 1999), pp. 740\u2013474. Morgan Kaufmann (1999)"},{"issue":"2-3","key":"9_CR7","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1023\/A:1017984413808","volume":"49","author":"M. Kearns","year":"2002","unstructured":"Kearns, M., Singh, S.: Near-optimal reinforcement learning in polynomial time. Machine Learning\u00a049(2-3), 209\u2013232 (2002)","journal-title":"Machine Learning"},{"key":"9_CR8","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/0004-3702(94)00087-H","volume":"76","author":"N. Kushmerick","year":"1995","unstructured":"Kushmerick, N., Hanks, S., Weld, D.S.: An algorithm for probabilistic planning. Artificial Intelligence\u00a076, 239\u2013286 (1995)","journal-title":"Artificial Intelligence"},{"key":"9_CR9","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s10994-010-5225-4","volume":"82","author":"L. Li","year":"2011","unstructured":"Li, L., Littman, M.L., Walsh, T.J., Strehl, A.L.: Knows what it knows: a framework for self-aware learning. Machine Learning\u00a082, 399\u2013443 (2011)","journal-title":"Machine Learning"},{"key":"9_CR10","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1613\/jair.2113","volume":"29","author":"H.M. Pasula","year":"2007","unstructured":"Pasula, H.M., Zettlemoyer, L.S., Kaelbling, L.P.: Learning symbolic models of stochastic domains. J. Artificial Intelligence Research\u00a029, 309\u2013352 (2007)","journal-title":"J. Artificial Intelligence Research"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Rodrigues, C., G\u00e9rard, P., Rouveirol, C., Soldano, H.: Incremental learning of relational action rules. In: Proc. 9th International Conference on Machine Learning and Applications (ICMLA 2010), pp. 451\u2013458. IEEE Computer Society (2010)","DOI":"10.1109\/ICMLA.2010.73"},{"key":"9_CR12","unstructured":"Strehl, A.L., Diuk, C., Littman, M.L.: Efficient structure learning in factored-state MDPs. In: Proc. 22nd AAAI Conference on Artificial Intelligence (AAAI 2007), pp. 645\u2013650. AAAI Press (2007)"},{"key":"9_CR13","unstructured":"Walsh, T.J., Szita, I., Diuk, C., Littman, M.L.: Exploring compact reinforcement-learning representations with linear regression. In: Proc. 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009 (2009)"},{"key":"9_CR14","unstructured":"Weissman, T., Ordentlich, E., Seroussi, G., Verdu, S., Weinberger, M.J.: Inequalities for the l\n                  1 deviation of the empirical distribution. Tech. Rep. HPL-2003-97, Hewlett-Packard Company (2003)"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-29946-9_9.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T11:22:34Z","timestamp":1620127354000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-29946-9_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642299452","9783642299469"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-29946-9_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}