{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T02:14:56Z","timestamp":1776737696179,"version":"3.51.2"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319235240","type":"print"},{"value":"9783319235257","type":"electronic"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-23525-7_20","type":"book-chapter","created":{"date-parts":[[2015,8,28]],"date-time":"2015-08-28T08:20:13Z","timestamp":1440750013000},"page":"327-342","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Planning in Discrete and Continuous Markov Decision Processes by Probabilistic Programming"],"prefix":"10.1007","author":[{"given":"Davide","family":"Nitti","sequence":"first","affiliation":[]},{"given":"Vaishak","family":"Belle","sequence":"additional","affiliation":[]},{"given":"Luc","family":"De Raedt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,8,29]]},"reference":[{"key":"20_CR1","unstructured":"Couetoux, A.: Monte Carlo Tree Search for Continuous and Stochastic Sequential Decision Making Problems. Universit\u00e9 Paris Sud - Paris XI, Thesis (2013)"},{"key":"20_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-78652-8_1","volume-title":"Probabilistic Inductive Logic Programming","author":"L De Raedt","year":"2008","unstructured":"De Raedt, L., Kersting, K.: Probabilistic inductive logic programming. In: De Raedt, L., Frasconi, P., Kersting, K., Muggleton, S.H. (eds.) Probabilistic Inductive Logic Programming. LNCS (LNAI), vol. 4911, pp. 1\u201327. Springer, Heidelberg (2008)"},{"key":"20_CR3","unstructured":"Driessens, K., Ramon, J.: Relational instance based regression for relational reinforcement learning. In: Proc. ICML (2003)"},{"key":"20_CR4","unstructured":"Feng, Z., Dearden, R., Meuleau, N., Washington, R.: Dynamic programming for structured continuous Markov decision problems. In: Proc. UAI (2004)"},{"key":"20_CR5","unstructured":"Forbes, J., Andr\u00e9, D.: Representations for learning control policies. In: Proc. of the ICML Workshop on Development of Representations (2002)"},{"key":"20_CR6","unstructured":"Goodman, N., Mansinghka, V.K., Roy, D.M., Bonawitz, K., Tenenbaum, J.B.: Church: A language for generative models. In: Proc. UAI, pp. 220\u2013229 (2008)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Gutmann, B., Thon, I., Kimmig, A., Bruynooghe, M., De Raedt, L.: The magic of logical inference in probabilistic programming. Theory and Practice of Logic Programming (2011)","DOI":"10.1017\/S1471068411000238"},{"key":"20_CR8","unstructured":"Kearns, M., Mansour, Y., Ng, A.Y.: A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes. Machine Learning (2002)"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Keller, T., Eyerich, P.: PROST: probabilistic planning based on UCT. In: Proc. ICAPS (2012)","DOI":"10.1609\/icaps.v22i1.13518"},{"key":"20_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/978-3-540-89982-2_22","volume-title":"Logic Programming","author":"A Kimmig","year":"2008","unstructured":"Kimmig, A., Santos Costa, V., Rocha, R., Demoen, B., De Raedt, L.: On the efficient execution of problog programs. In: Garcia de la Banda, M., Pontelli, E. (eds.) ICLP 2008. LNCS, vol. 5366, pp. 175\u2013189. Springer, Heidelberg (2008)"},{"key":"20_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based monte-carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282\u2013293. Springer, Heidelberg (2006)"},{"key":"20_CR12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.3093","volume":"39","author":"T Lang","year":"2010","unstructured":"Lang, T., Toussaint, M.: Planning with Noisy Probabilistic Relational Rules. Journal of Artificial Intelligence Research 39, 1\u201349 (2010)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Mansley, C.R., Weinstein, A., Littman, M.L.: Sample-Based planning for continuous action markov decision processes. In: Proc. ICAPS (2011)","DOI":"10.1609\/icaps.v21i1.13484"},{"issue":"1","key":"20_CR14","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1613\/jair.2529","volume":"34","author":"N Meuleau","year":"2009","unstructured":"Meuleau, N., Benazera, E., Brafman, R.I., Hansen, E.A., Mausam, M.: A heuristic search approach to planning with continuous resources in stochastic domains. Journal of Artificial Intelligence Research 34(1), 27 (2009)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"20_CR15","unstructured":"Milch, B., Marthi, B., Russell, S., Sontag, D., Ong, D., Kolobov, A.: BLOG: probabilistic models with unknown objects. In: Proc. IJCAI (2005)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Munos, R.: From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning. Foundations and Trends in Machine Learning, Now Publishers (2014)","DOI":"10.1561\/9781601987679"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Nitti, D., De Laet, T., De Raedt, L.: A particle filter for hybrid relational domains. In: Proc. IROS (2013)","DOI":"10.1109\/IROS.2013.6696747"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Nitti, D., De Laet, T., De Raedt, L.: Relational object tracking and learning. In: Proc. ICRA (2014)","DOI":"10.1109\/ICRA.2014.6906966"},{"key":"20_CR19","unstructured":"Owen, A.B.: Monte Carlo theory, methods and examples (2013)"},{"key":"20_CR20","unstructured":"Peshkin, L., Shelton, C.R.: Learning from scarce experience. In: Proc. ICML, pp. 498\u2013505 (2002)"},{"key":"20_CR21","unstructured":"Precup, D., Sutton, R.S., Singh, S.P.: Eligibility traces for off-policy policy evaluation. In: Proc. ICML (2000)"},{"key":"20_CR22","unstructured":"Sanner, S.: Relational Dynamic Influence Diagram Language (RDDL): Language Description (unpublished paper)"},{"key":"20_CR23","unstructured":"Sanner, S., Delgado, K.V., de Barros, L.N.: Symbolic dynamic programming for discrete and continuous state MDPs. In: Proc. UAI (2011)"},{"key":"20_CR24","unstructured":"Shelton, C.R.: Policy improvement for POMDPs using normalized importance sampling. In: Proc. UAI, pp. 496\u2013503 (2001)"},{"key":"20_CR25","unstructured":"Shelton, C.R.: Importance Sampling for Reinforcement Learning with Multiple Objectives. Ph.D. thesis, MIT (2001)"},{"key":"20_CR26","unstructured":"Smart, W.D., Kaelbling, L.P.: Practical reinforcement learning in continuous spaces. In: Proc. ICML (2000)"},{"key":"20_CR27","unstructured":"Srivastava, S., Russell, S., Ruan, P., Cheng, X.: First-order open-universe POMDPs. In: Proc. UAI (2014)"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Van den Broeck, G., Thon, I., van Otterlo, M., De Raedt, L.: DTProbLog: a decision-theoretic probabilistic prolog. In: Proc. AAAI (2010)","DOI":"10.1609\/aaai.v24i1.7755"},{"key":"20_CR30","unstructured":"Vien, N.A., Toussaint, M.: Model-Based relational RL when object existence is partially observable. In: Proc. ICML (2014)"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Walsh, T.J., Goschin, S., Littman, M.L.: Integrating sample-based planning and model-based reinforcement learning. In: Proc. AAAI (2010)","DOI":"10.1609\/aaai.v24i1.7689"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Wiering, M., van Otterlo, M.: Reinforcement learning: state-of-the-art. In: Adaptation, Learning, and Optimization. Springer (2012)","DOI":"10.1007\/978-3-642-27645-3"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-23525-7_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,13]],"date-time":"2023-08-13T13:52:34Z","timestamp":1691934754000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-23525-7_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319235240","9783319235257"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-23525-7_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"29 August 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}