{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T05:32:12Z","timestamp":1740461532224,"version":"3.37.3"},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642158827"},{"type":"electronic","value":"9783642158834"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15883-4_12","type":"book-chapter","created":{"date-parts":[[2010,8,17]],"date-time":"2010-08-17T09:29:46Z","timestamp":1282037386000},"page":"178-194","source":"Crossref","is-referenced-by-count":5,"title":["Exploration in Relational Worlds"],"prefix":"10.1007","author":[{"given":"Tobias","family":"Lang","sequence":"first","affiliation":[]},{"given":"Marc","family":"Toussaint","sequence":"additional","affiliation":[]},{"given":"Kristian","family":"Kersting","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proc.\u00a0of the Int.\u00a0Conf.\u00a0on Machine Learning (ICML), pp. 41\u201348 (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"12_CR2","unstructured":"Boutilier, C., Reiter, R., Price, B.: Symbolic dynamic programming for first-order MDPs. In: Proc.\u00a0of the Int.\u00a0Conf.\u00a0on Artificial Intelligence (IJCAI), pp. 690\u2013700 (2001)"},{"key":"12_CR3","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1162\/153244303765208377","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. Journal of Machine Learning Research\u00a03, 213\u2013231 (2002)","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"12_CR4","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1613\/jair.295","volume":"4","author":"D.A. Cohn","year":"1996","unstructured":"Cohn, D.A., Ghahramani, Z., Jordan, M.I.: Active learning with statistical models. Journal of Artificial Intelligence Research\u00a04(1), 129\u2013145 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"12_CR5","unstructured":"Croonenborghs, T., Ramon, J., Blockeel, H., Bruynooghe, M.: Online learning and exploiting relational models in reinforcement learning. In: Proc.\u00a0of the Int.\u00a0Conf.\u00a0on Artificial Intelligence (IJCAI), pp. 726\u2013731 (2007)"},{"issue":"3","key":"12_CR6","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1023\/B:MACH.0000039779.47329.3a","volume":"57","author":"K. Driessens","year":"2004","unstructured":"Driessens, K., D\u017eeroski, S.: Integrating guidance into relational reinforcement learning. Machine Learning\u00a057(3), 271\u2013304 (2004)","journal-title":"Machine Learning"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Driessens, K., Ramon, J., G\u00e4rtner, T.: Graph kernels and Gaussian processes for relational reinforcement learning. In: Machine Learning (2006)","DOI":"10.1007\/s10994-006-8258-y"},{"key":"12_CR8","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"},{"volume-title":"A Introduction to Statistical Relational Learning","year":"2007","key":"12_CR9","unstructured":"Getoor, L., Taskar, B. (eds.): A Introduction to Statistical Relational Learning. MIT Press, Cambridge (2007)"},{"key":"12_CR10","unstructured":"Guestrin, C., Patrascu, R., Schuurmans, D.: Algorithm-directed exploration for model-based reinforcement learning in factored MDPs. In: Proc.\u00a0of the Int.\u00a0Conf.\u00a0on Machine Learning (ICML), pp. 235\u2013242 (2002)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Halbritter, F., Geibel, P.: Learning models of relational MDPs using graph kernels. In: Proc.\u00a0of the Mexican Conf.\u00a0on A.I (MICAI), pp. 409\u2013419 (2007)","DOI":"10.1007\/978-3-540-76631-5_39"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Joshi, S., Kersting, K., Khardon, R.: Self-taught decision theoretic planning with first order decision diagrams. In: Proceedings of ICAPS 2010 (2010)","DOI":"10.1609\/icaps.v20i1.13411"},{"key":"12_CR13","unstructured":"Kearns, M., Koller, D.: Efficient reinforcement learning in factored MDPs. In: Proc.\u00a0of the Int.\u00a0Conf.\u00a0on Artificial Intelligence (IJCAI), pp. 740\u2013747 (1999)"},{"issue":"2-3","key":"12_CR14","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":"12_CR15","doi-asserted-by":"crossref","unstructured":"Kersting, K., Driessens, K.: Non\u2013parametric policy gradients: A unified treatment of propositional and relational domains. In: Proceedings of the 25th International Conference on Machine Learning (ICML 2008), July 5-9 (2008)","DOI":"10.1145\/1390156.1390214"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Lang, T., Toussaint, M.: Approximate inference for planning in stochastic relational worlds. In: Proc.\u00a0of the Int.\u00a0Conf.\u00a0on Machine Learning, ICML (2009)","DOI":"10.1145\/1553374.1553450"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Lang, T., Toussaint, M.: Relevance grounding for planning in relational domains. In: Proc. of the European Conf. on Machine Learning (ECML) (September 2009)","DOI":"10.1007\/978-3-642-04180-8_65"},{"key":"12_CR18","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. Artificial Intelligence Research\u00a029, 309\u2013352 (2007)","journal-title":"Artificial Intelligence Research"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Poupart, P., Vlassis, N., Hoey, J., Regan, K.: An analytic solution to discrete bayesian reinforcement learning. In: Proc.\u00a0of the Int.\u00a0Conf.\u00a0on Machine Learning (ICML), pp. 697\u2013704 (2006)","DOI":"10.1145\/1143844.1143932"},{"key":"12_CR20","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1007\/978-3-540-74958-5_70","volume-title":"Machine Learning: ECML 2007","author":"J. Ramon","year":"2007","unstructured":"Ramon, J., Driessens, K., Croonenborghs, T.: Transfer learning in reinforcement learning problems through partial policy recycling. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., Matwin, S., Mladeni\u010d, D., Skowron, A. (eds.) ECML 2007. LNCS (LNAI), vol.\u00a04701, pp. 699\u2013707. Springer, Heidelberg (2007)"},{"key":"12_CR21","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1016\/j.artint.2008.11.003","volume":"173","author":"S. Sanner","year":"2009","unstructured":"Sanner, S., Boutilier, C.: Practical solution techniques for first order MDPs. Artificial Intelligence Journal\u00a0173, 748\u2013788 (2009)","journal-title":"Artificial Intelligence Journal"},{"key":"12_CR22","volume-title":"Handbook for Intelligent Control: Neural, Fuzzy and Adaptive Approaches","author":"S. Thrun","year":"1992","unstructured":"Thrun, S.: The role of exploration in learning control. In: White, D., Sofge, D. (eds.) Handbook for Intelligent Control: Neural, Fuzzy and Adaptive Approaches, Van Nostrand Reinhold, Florence (1992)"},{"key":"12_CR23","unstructured":"Walsh, T.J.: Efficient learning of relational models for sequential decision making. PhD thesis, Rutgers, The State University of New Jersey, New Brunswick, NJ (2010)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15883-4_12.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:18:34Z","timestamp":1740421114000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15883-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642158827","9783642158834"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15883-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}