{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:02:45Z","timestamp":1742961765891,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642252549"},{"type":"electronic","value":"9783642252556"}],"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\/978-3-642-25255-6_52","type":"book-chapter","created":{"date-parts":[[2011,12,7]],"date-time":"2011-12-07T12:24:03Z","timestamp":1323260643000},"page":"407-414","source":"Crossref","is-referenced-by-count":0,"title":["Learning Form Experience: A Bayesian Network Based Reinforcement Learning Approach"],"prefix":"10.1007","author":[{"given":"Zhao","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiong","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"52_CR1","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"issue":"3","key":"52_CR2","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s10994-010-5182-y","volume":"81","author":"G. Sertan","year":"2010","unstructured":"Sertan, G., Faruk, P., Reda, A.: Improving reinforcement learning by using sequence trees. Machine Learning\u00a081(3), 283\u2013331 (2010)","journal-title":"Machine Learning"},{"issue":"4","key":"52_CR3","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1016\/j.neunet.2010.01.001","volume":"23","author":"M. Grzes","year":"2010","unstructured":"Grzes, M., Kudenko, D.: Online learning of shaping rewards in reinforcement learning. Neural Networks\u00a023(4), 541\u2013550 (2010)","journal-title":"Neural Networks"},{"key":"52_CR4","doi-asserted-by":"crossref","unstructured":"Wang, t., Daniel, L.: Bayesian Sparse Sampling for On-line Reward Optimization. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 956\u2013963 (2005)","DOI":"10.1145\/1102351.1102472"},{"key":"52_CR5","doi-asserted-by":"crossref","unstructured":"Amizadeh, S., Ahmadabadi, M.: A Bayesian Approach to Conceptualization Using Reinforcement Learning. In: 2007 International Conference on Advanced Intelligent Mechatronics, pp. 1\u20137 (2007)","DOI":"10.1109\/AIM.2007.4412531"},{"key":"52_CR6","doi-asserted-by":"crossref","unstructured":"Doshi, F., Pineau, J.: Reinforcement Learning with Limited Reinforcement: Using Bayes Risk for Active Learning in POMDPs, pp. 256\u2013263 (2008)","DOI":"10.1145\/1390156.1390189"},{"key":"52_CR7","doi-asserted-by":"crossref","unstructured":"Joseph, R., Peter, S.: Online Kernel Selection for Bayesian Reinforcement Learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 816\u2013823 (2008)","DOI":"10.1145\/1390156.1390259"},{"key":"52_CR8","unstructured":"Bob, P., Craig, B.: A Bayesian Approach to Imitation in Reinforcement Learning. In: Proceedings of IJCAI 2003, Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, pp. 712\u2013720 (2003)"},{"key":"52_CR9","first-page":"48","volume":"3","author":"H. Firouzi","year":"2008","unstructured":"Firouzi, H., Ahmadabadi, M.N.: A Probabilistic Reinforcement-Based Approach to Conceptualization. International Journal of Intelligent Systems and Technologies\u00a03, 48\u201355 (2008)","journal-title":"International Journal of Intelligent Systems and Technologies"},{"key":"52_CR10","first-page":"79","volume-title":"Probabilistic reasoning in intelligent systems: networks of plausible inference","author":"J. Pearl","year":"1988","unstructured":"Pearl, J.: Probabilistic reasoning in intelligent systems: networks of plausible inference, pp. 79\u2013119. Morgan Kaufmann, San Mateo (1988)"},{"key":"52_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/978-3-642-16167-4_7","volume-title":"Information Computing and Applications","author":"Z. Jin","year":"2010","unstructured":"Jin, Z., Jin, J., Liu, W.: Autonomous Discovery of Subgoals Using Acyclic State Trajectories. In: Zhu, R., Zhang, Y., Liu, B., Liu, C. (eds.) ICICA 2010. LNCS, vol.\u00a06377, pp. 49\u201356. Springer, Heidelberg (2010)"}],"container-title":["Lecture Notes in Computer Science","Information Computing and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-25255-6_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T01:53:21Z","timestamp":1742003601000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-25255-6_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642252549","9783642252556"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-25255-6_52","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}