{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T18:07:02Z","timestamp":1725732422047},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642387081"},{"type":"electronic","value":"9783642387098"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40988-2_1","type":"book-chapter","created":{"date-parts":[[2013,8,28]],"date-time":"2013-08-28T10:56:40Z","timestamp":1377687400000},"page":"1-16","source":"Crossref","is-referenced-by-count":14,"title":["A Cascaded Supervised Learning Approach to Inverse Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Edouard","family":"Klein","sequence":"first","affiliation":[]},{"given":"Bilal","family":"Piot","sequence":"additional","affiliation":[]},{"given":"Matthieu","family":"Geist","sequence":"additional","affiliation":[]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.: Apprenticeship learning via inverse reinforcement learning. In: Proc. ICML (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"1_CR2","unstructured":"Boularias, A., Kober, J.: Peters: Relative entropy inverse reinforcement learning. In: Proc. ICAPS, vol.\u00a015, pp. 20\u201327 (2011)"},{"key":"1_CR3","unstructured":"Dvijotham, K., Todorov, E.: Inverse optimal control with linearly-solvable MDPs. In: Proc. ICML (2010)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Guermeur, Y.: A generic model of multi-class support vector machine. International Journal of Intelligent Information and Database Systems (2011)","DOI":"10.1504\/IJIIDS.2012.050094"},{"key":"1_CR5","unstructured":"Klein, E., Geist, M., Piot, B., Pietquin, O.: Inverse Reinforcement Learning through Structured Classification. In: Proc. NIPS, Lake Tahoe, NV, USA (December 2012)"},{"key":"1_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-642-15883-4_25","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"F.S. Melo","year":"2010","unstructured":"Melo, F.S., Lopes, M.: Learning from demonstration using MDP induced metrics. In: Balc\u00e1zar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010, Part II. LNCS, vol.\u00a06322, pp. 385\u2013401. Springer, Heidelberg (2010)"},{"key":"1_CR7","unstructured":"Melo, F., Lopes, M., Ferreira, R.: Analysis of inverse reinforcement learning with perturbed demonstrations. In: Proc. ECAI, pp. 349\u2013354. IOS Press (2010)"},{"issue":"2","key":"1_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s10994-009-5110-1","volume":"77","author":"G. Neu","year":"2009","unstructured":"Neu, G., Szepesv\u00e1ri, C.: Training parsers by inverse reinforcement learning. Machine Learning\u00a077(2), 303\u2013337 (2009)","journal-title":"Machine Learning"},{"key":"1_CR9","unstructured":"Ng, A., Russell, S.: Algorithms for inverse reinforcement learning. In: Proc. ICML, pp. 663\u2013670. Morgan Kaufmann Publishers Inc. (2000)"},{"key":"1_CR10","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"M. Puterman","year":"1994","unstructured":"Puterman, M.: Markov decision processes: Discrete stochastic dynamic programming. John Wiley & Sons, Inc., New York (1994)"},{"key":"1_CR11","volume-title":"Gaussian processes for machine learning","author":"C. Rasmussen","year":"2006","unstructured":"Rasmussen, C., Williams, C.: Gaussian processes for machine learning, vol.\u00a01. MIT press, Cambridge (2006)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Ratliff, N., Bagnell, J., Srinivasa, S.: Imitation learning for locomotion and manipulation. In: International Conference on Humanoid Robots, pp. 392\u2013397. IEEE (2007)","DOI":"10.21236\/ADA528601"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Ratliff, N., Bagnell, J., Zinkevich, M.: Maximum margin planning. In: Proc. ICML, p. 736. ACM (2006)","DOI":"10.1145\/1143844.1143936"},{"key":"1_CR14","unstructured":"Regan, K., Boutilier, C.: Robust online optimization of reward-uncertain MDPs. In: Proc. IJCAI 2011 (2011)"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Russell, S.: Learning agents for uncertain environments (extended abstract). In: Annual Conference on Computational Learning Theory, p. 103. ACM (1998)","DOI":"10.1145\/279943.279964"},{"key":"1_CR16","unstructured":"Sutton, R., Barto, A.: Reinforcement learning. MIT Press (1998)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Syed, U., Bowling, M., Schapire, R.: Apprenticeship learning using linear programming. In: Proc. ICML, pp. 1032\u20131039. ACM (2008)","DOI":"10.1145\/1390156.1390286"},{"key":"1_CR18","unstructured":"Syed, U., Schapire, R.: A game-theoretic approach to apprenticeship learning. In: Proc. NIPS, vol.\u00a020, pp. 1449\u20131456 (2008)"},{"key":"1_CR19","unstructured":"Syed, U., Schapire, R.: A reduction from apprenticeship learning to classification. In: Proc. NIPS, vol.\u00a024, pp. 2253\u20132261 (2010)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Taskar, B., Chatalbashev, V., Koller, D., Guestrin, C.: Learning structured prediction models: A large margin approach. In: Proc. ICML, p. 903. ACM (2005)","DOI":"10.1145\/1102351.1102464"}],"container-title":["Lecture Notes in Computer Science","Advanced Information Systems Engineering"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40988-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T23:39:03Z","timestamp":1558049943000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40988-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387081","9783642387098"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40988-2_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}