{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:16:31Z","timestamp":1742962591723,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":29,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642239625"},{"type":"electronic","value":"9783642239632"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-23963-2_39","type":"book-chapter","created":{"date-parts":[[2011,10,5]],"date-time":"2011-10-05T21:29:02Z","timestamp":1317850142000},"page":"504-519","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Act Optimally in Partially Observable Markov Decision Processes Using Hybrid Probabilistic Logic Programs"],"prefix":"10.1007","author":[{"given":"Emad","family":"Saad","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"39_CR1","unstructured":"Baral, C., Tran, N., Tuan, L.C.: Reasoning about actions in a probabilistic setting. In: AAAI 2002 (2002)"},{"key":"39_CR2","volume-title":"Neural Information Processing Systems","author":"J. Bagnell","year":"2003","unstructured":"Bagnell, J., Kakade, S., Ng, A., Schneider, J.: Policy search by dynamic programming. In: Neural Information Processing Systems, vol.\u00a016. MIT Press, Cambridge (2003)"},{"key":"39_CR3","first-page":"1","volume":"11","author":"C. Boutilier","year":"1999","unstructured":"Boutilier, C., Dean, T., Hanks, S.: Decision-theoretic planning: structural assumptions and computational leverage. Journal of AI Research\u00a011, 1\u201394 (1999)","journal-title":"Journal of AI Research"},{"key":"39_CR4","unstructured":"Boutilier, C., Reiter, R., Price, B.: Symbolic dynamic programming for first-order MDPs. In: 17th IJCAI (2001)"},{"key":"39_CR5","unstructured":"Draper, D., Hanks, S., Weld, D.: Probabilistic planning with information gathering and contingent execution. In: 2nd ICAIPS (1994)"},{"key":"39_CR6","unstructured":"Eiter, T., Lukasiewicz, T.: Probabilistic reasoning about actions in nonmonotonic causal theories. In: 19th Conference on Uncertainty in Artificial Intelligence (2003)"},{"key":"39_CR7","volume-title":"ICSLP","author":"M. Gelfond","year":"1988","unstructured":"Gelfond, M., Lifschitz, V.: The stable model semantics for logic programming. In: ICSLP. MIT Press, Cambridge (1988)"},{"issue":"3-4","key":"39_CR8","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/BF03037169","volume":"9","author":"M. Gelfond","year":"1991","unstructured":"Gelfond, M., Lifschitz, V.: Classical negation in logic programs and disjunctive databases. New Generation Computing\u00a09(3-4), 363\u2013385 (1991)","journal-title":"New Generation Computing"},{"key":"39_CR9","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/0743-1066(93)90035-F","volume":"17","author":"M. Gelfond","year":"1993","unstructured":"Gelfond, M., Lifschitz, V.: Representing action and change by logic programs. Journal of Logic Programming\u00a017, 301\u2013321 (1993)","journal-title":"Journal of Logic Programming"},{"key":"39_CR10","unstructured":"Iocchi, L., Lukasiewicz, T., Nardi, D., Rosati, R.: Reasoning about actions with sensing under qualitative and probabilistic uncertainty. In: 16th ECAI (2004)"},{"key":"39_CR11","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"L. Kaelbling","year":"1998","unstructured":"Kaelbling, L., Littman, M., Cassandra, A.: Planning and acting in partially observable stochastic domains. Artificial Intelligence\u00a0101, 99\u2013134 (1998)","journal-title":"Artificial Intelligence"},{"key":"39_CR12","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L. Kaelbling","year":"1996","unstructured":"Kaelbling, L., Littman, M., Moore, A.: Reinforcement Learning: A Survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"39_CR13","unstructured":"Kautz, H., Selman, B.: Pushing the envelope: planning, propositional logic, and stochastic search. In: 13th National Conference on Artificial Intelligence (1996)"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Kersting, K., De Raedt, L.: Logical Markov decision programs and the convergence of logical TD(\u03bb). In: 14th International Conference on Inductive Logic Programming (2004)","DOI":"10.1007\/978-3-540-30109-7_16"},{"issue":"1-2","key":"39_CR15","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.: An algorithm for probabilistic planning. Artificial Intelligence\u00a076(1-2), 239\u2013286 (1995)","journal-title":"Artificial Intelligence"},{"issue":"1-2","key":"39_CR16","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.artint.2004.04.004","volume":"157","author":"F. Lin","year":"2004","unstructured":"Lin, F., Zhao, Y.: ASSAT: Computing answer sets of a logic program by SAT solvers. Artificial Intelligence\u00a0157(1-2), 115\u2013137 (2004)","journal-title":"Artificial Intelligence"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Littman, M., Cassandra, A., Kaelbling, L.: Learning policies for partially observable environments: scaling up. In: 12th ICML (1995)","DOI":"10.1016\/B978-1-55860-377-6.50052-9"},{"issue":"1\u20132","key":"39_CR18","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/S0004-3702(02)00379-X","volume":"147","author":"S. Majercik","year":"2003","unstructured":"Majercik, S., Littman, M.: Contingent planning under uncertainty via stochastic satisfiability. Artificial Intelligence\u00a0147(1\u20132), 119\u2013162 (2003)","journal-title":"Artificial Intelligence"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Mundhenk, M., Goldsmith, J., Lusena, C., Allender, E.: Complexity of finite-horizon Markov decision process problems. Journal of the ACM (2000)","DOI":"10.1145\/347476.347480"},{"key":"39_CR20","unstructured":"Niemela, I., Simons, P.: Efficient implementation of the well-founded and stable model semantics. In: Joint ICSLP, pp. 289\u2013303 (1996)"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Saad, E.: Incomplete knowlege in hybrid probabilistic logic programs. In: 10th European Conference on Logics in Artificial Intelligence (2006)","DOI":"10.1007\/11853886_33"},{"key":"39_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/978-3-642-04388-8_17","volume-title":"Scalable Uncertainty Management","author":"E. Saad","year":"2009","unstructured":"Saad, E.: Probabilistic planning with imperfect sensing actions using hybrid probabilistic logic programs. In: Godo, L., Pugliese, A. (eds.) SUM 2009. LNCS, vol.\u00a05785, pp. 206\u2013222. Springer, Heidelberg (2009)"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Saad, E.: A logical framework to reinforcement learning using hybrid probabilistic logic programs. In: 2nd International Conference on Scalable Uncertainty Management (2008)","DOI":"10.1007\/978-3-540-87993-0_27"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Saad, E.: On the relationship between hybrid probabilistic logic programs and stochastic satisfiability. In: 2nd International Conference on Scalable Uncertainty Management (2008)","DOI":"10.1007\/978-3-540-87993-0_28"},{"key":"39_CR25","doi-asserted-by":"crossref","unstructured":"Saad, E.: Probabilistic planning in hybrid probabilistic logic programs. In: 1st International Conference on Scalable Uncertainty Management (2007)","DOI":"10.1007\/978-3-540-75410-7_1"},{"issue":"3-4","key":"39_CR26","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s10472-007-9048-3","volume":"48","author":"E. Saad","year":"2006","unstructured":"Saad, E., Pontelli, E.: A new approach to hybrid probabilistic logic programs. Annals of Mathematics and Artificial Intelligence Journal\u00a048(3-4), 187\u2013243 (2006)","journal-title":"Annals of Mathematics and Artificial Intelligence Journal"},{"key":"39_CR27","unstructured":"Scherl, R., Levesque, H.: The frame problem and knowledge producing actions. In: AAAI 1993 (1993)"},{"issue":"4","key":"39_CR28","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1145\/1183278.1183279","volume":"7","author":"T. Son","year":"2006","unstructured":"Son, T., Baral, C., Nam, T., McIlraith, S.: Domain-dependent knowledge in answer set planning. ACM Transactions on Computational Logic\u00a07(4), 613\u2013657 (2006)","journal-title":"ACM Transactions on Computational Logic"},{"key":"39_CR29","volume-title":"Reinforcement Learning: An Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"}],"container-title":["Lecture Notes in Computer Science","Scalable Uncertainty Management"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23963-2_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T19:57:36Z","timestamp":1558295856000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23963-2_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642239625","9783642239632"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23963-2_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}