{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:26:31Z","timestamp":1725470791918},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540459071"},{"type":"electronic","value":"9783540459095"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11881223_118","type":"book-chapter","created":{"date-parts":[[2006,9,22]],"date-time":"2006-09-22T11:45:14Z","timestamp":1158925514000},"page":"928-937","source":"Crossref","is-referenced-by-count":0,"title":["Unique State and Automatical Action Abstracting Based on Logical MDPs with Negation"],"prefix":"10.1007","author":[{"given":"Song","family":"Zhiwei","sequence":"first","affiliation":[]},{"given":"Chen","family":"Xiaoping","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"118_CR1","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":"118_CR2","volume-title":"Reinforcement Learning: An Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"118_CR3","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":"118_CR4","unstructured":"Driessens, K., Ramon, J.: Relational instrance based regression for relational reinforcement learning. In: ICML 2003 (2003)"},{"key":"118_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/978-3-540-39917-9_11","volume-title":"Inductive Logic Programming","author":"T. G\u00e4rtner","year":"2003","unstructured":"G\u00e4rtner, T., Driessens, K., Ramon, J.: Graph kernels and gaussian processes for relational reinforcement learning. In: Horv\u00e1th, T., Yamamoto, A. (eds.) ILP 2003. LNCS, vol.\u00a02835, pp. 146\u2013163. Springer, Heidelberg (2003)"},{"key":"118_CR6","unstructured":"Cole, J., Lloyd, K., Ng, K.: Symbolic learning for adaptive agents. In: The Annual Partner Conference, Smart Internet Technology Cooperative Research Centre (2003)"},{"key":"118_CR7","unstructured":"Yoon, S., Fern, A., Givan, R.: Inductive policy selection for first-order MDPs. In: UAI 2002 (2002)"},{"key":"118_CR8","unstructured":"Fern, A., Yoon, S., Givan, R.: Approximate policy iteration with a policy language bias. In: NIPS 2003 (2003)"},{"key":"118_CR9","unstructured":"Boutilier, C., Reiter, R., Price, B.: Symbolic dynamic programming for first-order MDPs. In: Seventeenth International Joint Conference on Artificial Intelligence (IJCAI 2001), pp. 690\u2013700 (2001)"},{"key":"118_CR10","unstructured":"Kersting, K., De Raedt, L.: Logical markov decision programs. In: IJCAI 2003 Workshop on Learning Statistical Models of Relational Data (2003)"},{"key":"118_CR11","unstructured":"Van Otterlo, M.: Reinforcement learning for relational MDPs. In: Machine Learning Conference of Belgium and the Netherlands (BeNeLearn 2004) (2004)"},{"key":"118_CR12","unstructured":"Morales, E.: Scaling up reinforcement learning with a relational representation. In: Proceedings of the Workshop on Adaptability in Multi-agent Systems at AORC 2003, Sydney (2003)"},{"key":"118_CR13","unstructured":"Guestrin, C., Koller, D., Gearhart, C., Kanodia, N.: Generalizing plans to new environments in relational MDPs. In: IJCAI 2003 (2003)"},{"key":"118_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/978-3-540-30109-7_16","volume-title":"Inductive Logic Programming","author":"K. Kersting","year":"2004","unstructured":"Kersting, K., De Raedt, L.: Logical markov decision programs and the convergence of logical TD(\u03bb). In: Camacho, R., King, R., Srinivasan, A. (eds.) ILP 2004. LNCS, vol.\u00a03194, pp. 180\u2013197. Springer, Heidelberg (2004)"},{"key":"118_CR15","series-title":"Lecture Notes in Artifical Intelligence","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-62927-0","volume-title":"Foundations of Inductive Logic Programming","author":"S.-H. Nienhuys-Cheng","year":"1997","unstructured":"Nienhuys-Cheng, S.-H., de Wolf, R.: Foundations of Inductive Logic Programming. Lecture Notes in Artifical Intelligence, vol.\u00a01228. Springer, Heidelberg (1997)"},{"key":"118_CR16","doi-asserted-by":"crossref","unstructured":"Clark, K.L.: Negation as failure. In: Logic and Data Bases, pp. 293\u2013322 (1977)","DOI":"10.1007\/978-1-4684-3384-5_11"},{"key":"118_CR17","unstructured":"Van Otterlo, M., Kersting, K.: Challenges for relational reinforcement learning. In: ICML 2004 Workshop on Relational Reinforcement Learning (2004)"},{"key":"118_CR18","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/S0004-3702(00)00079-5","volume":"125","author":"J. Slaney","year":"2001","unstructured":"Slaney, J., Thi\u00e9baux, S.: Blocks world revisited. Artificial Intelligence\u00a0125, 119\u2013153 (2001)","journal-title":"Artificial Intelligence"},{"key":"118_CR19","doi-asserted-by":"crossref","unstructured":"Kersting, K., Van Otterlo, M., De Raedt, L.: Bellman goes relational. In: ICML 2004 (2004)","DOI":"10.1145\/1015330.1015401"},{"key":"118_CR20","doi-asserted-by":"crossref","unstructured":"Lecoeuche, R.: Learning optimal dialogue management rules by using reinforcement learning and inductive logic programming. In: Proc. of the North American Chapter of the Association for Computational Linguistics (NAACL) (2001)","DOI":"10.3115\/1073336.1073364"}],"container-title":["Lecture Notes in Computer Science","Advances in Natural Computation"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11881223_118.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T14:50:42Z","timestamp":1605624642000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11881223_118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540459071","9783540459095"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/11881223_118","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}