{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T18:07:12Z","timestamp":1725732432815},"publisher-location":"Berlin, Heidelberg","reference-count":12,"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_2","type":"book-chapter","created":{"date-parts":[[2013,8,28]],"date-time":"2013-08-28T06:56:40Z","timestamp":1377673000000},"page":"17-32","source":"Crossref","is-referenced-by-count":7,"title":["Learning from Demonstrations: Is It Worth Estimating a Reward Function?"],"prefix":"10.1007","author":[{"given":"Bilal","family":"Piot","sequence":"first","affiliation":[]},{"given":"Matthieu","family":"Geist","sequence":"additional","affiliation":[]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the 21st International Conference on Machine Learning, ICML (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Archibald, T., McKinnon, K., Thomas, L.: On the generation of markov decision processes. Journal of the Operational Research Society (1995)","DOI":"10.2307\/2584329"},{"key":"2_CR3","unstructured":"Atkeson, C.G., Schaal, S.: Robot learning from demonstration. In: Proceedings of the 14th International Conference on Machine Learning, ICML (1997)"},{"key":"2_CR4","unstructured":"Boularias, A., Kober, J., Peters, J.: Relative entropy inverse reinforcement learning. In: JMLR Workshop and Conference Proceedings, AISTATS 2011, vol.\u00a015 (2011)"},{"key":"2_CR5","unstructured":"Klein, E., Geist, M., Piot, B., Pietquin, O.: Inverse reinforcement learning through structured classification. In: Advances in Neural Information Processing Systems 25 (NIPS) (2012)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Langford, J., Zadrozny, B.: Relating reinforcement learning performance to classification performance. In: Proceedings of the 22nd International Conference on Machine Learning, ICML (2005)","DOI":"10.1145\/1102351.1102411"},{"key":"2_CR7","unstructured":"Pomerleau, D.: Alvinn: An autonomous land vehicle in a neural network. Tech. rep., DTIC Document (1989)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Russell, S.: Learning agents for uncertain environments. In: Proceedings of the 11th Annual Conference on Computational Learning Theory, COLT (1998)","DOI":"10.1145\/279943.279964"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Shor, N.Z., Kiwiel, K.C., Ruszcaynski, A.: Minimization methods for non-differentiable functions. Springer (1985)","DOI":"10.1007\/978-3-642-82118-9"},{"key":"2_CR10","unstructured":"Syed, U., Schapire, R.: A game-theoretic approach to apprenticeship learning. In: Advances in Neural Information Processing Systems 21 (NIPS) (2008)"},{"key":"2_CR11","unstructured":"Syed, U., Schapire, R.: A reduction from apprenticeship learning to classification. In: Advances in Neural Information Processing Systems 23 (NIPS) (2010)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Taskar, B., Chatalbashev, V., Koller, D., Guestrin, C.: Learning structured prediction models: A large margin approach. In: Proceedings of the 22nd International Conference on Machine Learning, ICML (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_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T19:31:30Z","timestamp":1558035090000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40988-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387081","9783642387098"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40988-2_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}