{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:33:39Z","timestamp":1725471219204},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540454625"},{"type":"electronic","value":"9783540454649"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11874850_31","type":"book-chapter","created":{"date-parts":[[2006,10,9]],"date-time":"2006-10-09T15:50:42Z","timestamp":1160409042000},"page":"268-277","source":"Crossref","is-referenced-by-count":4,"title":["A Hybrid Learning Strategy for Discovery of Policies of Action"],"prefix":"10.1007","author":[{"given":"Richardson","family":"Ribeiro","sequence":"first","affiliation":[]},{"given":"Fabr\u00edcio","family":"Enembreck","sequence":"additional","affiliation":[]},{"given":"Alessandro L.","family":"Koerich","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"1","key":"31_CR1","first-page":"37","volume":"6","author":"D.W. Aha","year":"1991","unstructured":"Aha, D.W., Kibler, D., Albert, M.K.: Instance-based Learning Algorithms. Machine Learning\u00a06(1), 37\u201366 (1991)","journal-title":"Machine Learning"},{"key":"31_CR2","series-title":"LNAI","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-540-28645-5_48","volume-title":"Advances in Artificial Intelligence \u2013 SBIA 2004","author":"A. Almeida","year":"2004","unstructured":"Almeida, A., Ramalho, G.L., Santana, H.P., Tedesco, P., Menezes, T.R., Corruble, V., Chevaleyre, Y.: Recent Advances on Multi-Agent Patrolling. In: Bazzan, A.L.C., Labidi, S. (eds.) SBIA 2004. LNCS (LNAI), vol.\u00a03171, pp. 474\u2013483. Springer, Heidelberg (2004)"},{"key":"31_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/978-3-540-28645-5_25","volume-title":"Advances in Artificial Intelligence \u2013 SBIA 2004","author":"R.A.C. Bianchi","year":"2004","unstructured":"Bianchi, R.A.C., Ribeiro, C.H.C., Costa, A.H.R.: Heuristically Accelerated Q-learning: A New Approach to Speed Up Reinforcement Learning. In: Bazzan, A.L.C., Labidi, S. (eds.) SBIA 2004. LNCS, vol.\u00a03171, pp. 245\u2013254. Springer, Heidelberg (2004)"},{"issue":"3","key":"31_CR4","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1023\/A:1011953410319","volume":"2","author":"K.L. Downing","year":"2001","unstructured":"Downing, K.L.: Reinforced Genetic Programming. Genetic Programming and Evolvable Machines\u00a02(3), 259\u2013288 (2001)","journal-title":"Genetic Programming and Evolvable Machines"},{"key":"31_CR5","first-page":"503","volume":"6","author":"D. Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., Wehenke, L.: Tree-Based Batch Mode Reinforcement learning. Journal of Machine Learning Research\u00a06, 503\u2013556 (2005)","journal-title":"Journal of Machine Learning Research"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Figueiredo, K., Vellasco, M., Pacheco, M., Souza, M.: Reinforcement Learning Hierarchical Neuro-Fuzzy Politree Model for Control of Autonomous Agents. In: Fourth Int. Conference on Hybrid Intelligent Systems (HIS 2004), pp. 130\u2013135 (2004)","DOI":"10.1109\/ICHIS.2004.80"},{"key":"31_CR7","unstructured":"Henderson, J., Lemon, O., Georgila, K.: Hybrid reinforcement\/supervised learning for dialogue policies from COMMUNICATOR data. In: Proc. IJCAI workshop on Knowledge and Reasoning in Practical Dialogue Systems, Edinburgh (2005)"},{"key":"31_CR8","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement Learning: A survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"31_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/3-540-45622-8_23","volume-title":"Abstraction, Reformulation, and Approximation","author":"I. Levner","year":"2002","unstructured":"Levner, I., Bulitko, V., Madani, O., Greiner, R.: Performance of lookahead control policies in the face of abstractions and approximations. In: Koenig, S., Holte, R.C. (eds.) SARA 2002. LNCS, vol.\u00a02371, pp. 299\u2013307. Springer, Heidelberg (2002); Maes, P.: Artificial Life Meets Entertainment: Lifelike Autonomous Agents. Communications of ACM 38(11), 108-114 (1995)"},{"key":"31_CR10","volume-title":"Machine Learning","author":"T. Mitchell","year":"1997","unstructured":"Mitchell, T.: Machine Learning. McGraw-Hill, Boston (1997)"},{"key":"31_CR11","unstructured":"Ramon, J.: On the convergence of reinforcement learning using a decision tree learner. In: Proceedings of ICML 2005 Workshop on Rich Representation for Reinforcement Learning, Bonn, Germany (2005)"},{"key":"31_CR12","volume-title":"Int. Joint Conference on Neuronal Networks","author":"C.H.C. Ribeiro","year":"1999","unstructured":"Ribeiro, C.H.C.: A Tutorial on Reinforcement Learning Techniques. In: Int. Joint Conference on Neuronal Networks. INNS Press, Washington (1999)"},{"key":"31_CR13","volume-title":"Intelig\u00eancia Artificial","author":"S. Russel","year":"2004","unstructured":"Russel, S., Norvig, P.: Intelig\u00eancia Artificial, 2nd edn. Editora Elsevier, Rio de Janeiro (2004)","edition":"2"},{"key":"31_CR14","unstructured":"Ryan, M.R.K.: Hierarchical Reinforcement Learning: A Hybrid Approach. PhD Thesis, University of New South Wales, School of Computer Science and Engineering (2004)"},{"key":"31_CR15","first-page":"1122","volume-title":"Proc. 3rd International Joint Conference on Autonomous Agents and Multi-Agents Systems (AAMAS\u201904)","author":"H. Santana","year":"2004","unstructured":"Santana, H., Ramalho, G., Corruble, V., Ratitch, B.: Multi-Agent Patrolling with Reinforcement Learning. In: Proc. 3rd International Joint Conference on Autonomous Agents and Multi-Agents Systems (AAMAS 2004), pp. 1122\u20131129. ACM, New York (2004)"},{"key":"31_CR16","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/0167-8655(89)90037-8","volume":"10","author":"W. Siedlecki","year":"1989","unstructured":"Siedlecki, W., Sklansky, J.: A note on Genetic Algorithms for Large-Scale Selection. Pattern Recognition Letters\u00a010, 335\u2013347 (1989)","journal-title":"Pattern Recognition Letters"},{"key":"31_CR17","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"3","key":"31_CR18","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G. Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal Difference Learning and TD-Gammon. Communications of the ACM\u00a038(3), 58\u201368 (1995)","journal-title":"Communications of the ACM"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning, Machine Learning, 8th edn., pp. 279\u2013292 (1992)","DOI":"10.1023\/A:1022676722315"}],"container-title":["Lecture Notes in Computer Science","Advances in Artificial Intelligence - IBERAMIA-SBIA 2006"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11874850_31.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T19:47:42Z","timestamp":1605642462000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11874850_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540454625","9783540454649"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/11874850_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}