{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:31:58Z","timestamp":1771702318188,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642041730","type":"print"},{"value":"9783642041747","type":"electronic"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"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":[[2009]]},"DOI":"10.1007\/978-3-642-04174-7_3","type":"book-chapter","created":{"date-parts":[[2009,8,26]],"date-time":"2009-08-26T20:52:46Z","timestamp":1251319966000},"page":"31-46","source":"Crossref","is-referenced-by-count":65,"title":["Active Learning for Reward Estimation in Inverse Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Manuel","family":"Lopes","sequence":"first","affiliation":[]},{"given":"Francisco","family":"Melo","sequence":"additional","affiliation":[]},{"given":"Luis","family":"Montesano","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Lopes, M., Melo, F., Kenward, B., Santos-Victor, J.: A computational model of social-learning mechanisms. Adaptive Behavior (to appear, 2009)","DOI":"10.1177\/1059712309342757"},{"key":"3_CR2","unstructured":"Melo, F., Lopes, M., Santos-Victor, J., Ribeiro, M.: A unified framework for imitation-like behaviors. In: Proc. 4th Int. Symp. Imitation in Animals and Artifacts (2007)"},{"key":"3_CR3","unstructured":"Ng, A., Russell, S.: Algorithms for inverse reinforcement learning. In: Proc. 17th Int. Conf. Machine Learning, pp. 663\u2013670 (2000)"},{"key":"3_CR4","unstructured":"Neu, G., Szepesv\u00e1ri, C.: Apprenticeship learning using inverse reinforcement learning and gradient methods. In: Proc. 23rd Conf. Uncertainty in Artificial Intelligence, pp. 295\u2013302 (2007)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.: Apprenticeship learning via inverse reinforcement learning. In: Proc. 21st Int. Conf. Machine Learning, pp. 1\u20138 (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"3_CR6","unstructured":"Ramachandran, D., Amir, E.: Bayesian inverse reinforcement learning. In: Proc. 20th Int. Joint Conf. Artificial Intelligence, pp. 2586\u20132591 (2007)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Syed, U., Schapire, R., Bowling, M.: Apprenticeship learning using linear programming. In: Proc. 25th Int. Conf. Machine Learning, pp. 1032\u20131039 (2008)","DOI":"10.1145\/1390156.1390286"},{"key":"3_CR8","unstructured":"Ziebart, B., Maas, A., Bagnell, J., Dey, A.: Maximum entropy inverse reinforcement learning. In: Proc. 23rd AAAI Conf. Artificial Intelligence, pp. 1433\u20131438 (2008)"},{"key":"3_CR9","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: Theory and application to reward shaping. In: Proc. 16th Int. Conf. Machine Learning, pp. 278\u2013287 (1999)"},{"key":"3_CR10","unstructured":"Settles, B.: Active learning literature survey. CS Tech. Rep.\u00a01648, Univ. Wisconsin-Madison (2009)"},{"key":"3_CR11","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1020281327116","volume":"50","author":"C. Andrieu","year":"2003","unstructured":"Andrieu, C., de Freitas, N., Doucet, A., Jordan, M.: An introduction to MCMC for machine learning. Machine Learning\u00a050, 5\u201343 (2003)","journal-title":"Machine Learning"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Timmer, S., Riedmiller, M.: Fitted Q-iteration with CMACs. In: Int. Symp. Approximate Dynamic Programming and Reinforcement Learning (2007)","DOI":"10.1109\/ADPRL.2007.368162"}],"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\/978-3-642-04174-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,22]],"date-time":"2019-05-22T01:57:53Z","timestamp":1558490273000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-04174-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642041730","9783642041747"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-04174-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009]]}}}