{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T20:43:18Z","timestamp":1794343398177,"version":"4.9.0"},"publisher-location":"Berlin, Heidelberg","reference-count":8,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540466499","type":"print"},{"value":"9783540466505","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11894841_6","type":"book-chapter","created":{"date-parts":[[2006,10,4]],"date-time":"2006-10-04T07:29:53Z","timestamp":1159946993000},"page":"29-31","source":"Crossref","is-referenced-by-count":3,"title":["Reinforcement Learning and Apprenticeship Learning for Robotic Control"],"prefix":"10.1007","author":[{"given":"Andrew Y.","family":"Ng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proc. ICML (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Exploration and apprenticeship learning in reinforcement learning. In: Proc. ICML (2005)","DOI":"10.1145\/1102351.1102352"},{"key":"6_CR3","unstructured":"Bagnell, J.A., Kakade, S., Ng, A.Y., Schneider, J.: Policy search by dynamic programming. In: NIPS\u00a016 (2003)"},{"key":"6_CR4","unstructured":"Demiris, J., Hayes, G.: A robot controller using learning by imitation (1994)"},{"key":"6_CR5","unstructured":"Kearns, M., Singh, S.: Near-optimal reinforcement learning in polynomial time. Machine Learning journal (2002)"},{"key":"6_CR6","first-page":"799","volume":"10","author":"Y. Kuniyoshi","year":"1994","unstructured":"Kuniyoshi, Y., Inaba, M., Inoue, H.: Learning by watching: Extracting reusable task knowledge from visual observation of human performance. T-RA\u00a010, 799\u2013822 (1994)","journal-title":"T-RA"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Langford, J., Zadrozny, B.: Relating reinforcement learning performance to classification performance. In: Proc. ICML (2005)","DOI":"10.1145\/1102351.1102411"},{"key":"6_CR8","unstructured":"Ng, A.Y., Russell, S.: Algorithms for inverse reinforcement learning. In: Proc. ICML (2000)"}],"container-title":["Lecture Notes in Computer Science","Algorithmic Learning Theory"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11894841_6.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T03:36:39Z","timestamp":1619494599000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11894841_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540466499","9783540466505"],"references-count":8,"URL":"https:\/\/doi.org\/10.1007\/11894841_6","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/11894841","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006]]}}}