{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T15:46:54Z","timestamp":1791820014356,"version":"4.3.4"},"publisher-location":"Boston, MA","reference-count":11,"publisher":"Springer US","isbn-type":[{"value":"9781489976857","type":"print"},{"value":"9781489976871","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-1-4899-7687-1_142","type":"book-chapter","created":{"date-parts":[[2019,3,20]],"date-time":"2019-03-20T15:32:23Z","timestamp":1553095943000},"page":"678-682","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Inverse Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Pieter","family":"Abbeel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew Y.","family":"Ng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,4,14]]},"reference":[{"key":"142_CR9123","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430","volume-title":"Apprenticeship learning via inverse reinforcement learning","author":"P Abbeel","year":"2004","unstructured":"Abbeel P, Ng AY (2004) Apprenticeship learning via inverse reinforcement learning. In: Proceedings of ICML, Alberta"},{"key":"142_CR9124","first-page":"101","volume":"7","author":"K Doya","year":"1995","unstructured":"Doya K, Sejnowski T (1995) A novel reinforcement model of birdsong vocalization learning. Neural Inf Process Syst 7:101","journal-title":"Neural Inf Process Syst"},{"issue":"6551","key":"142_CR9125","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1038\/377725a0","volume":"377","author":"PR Montague","year":"1995","unstructured":"Montague PR, Dayan P, Person C, Sejnowski TJ (1995) Bee foragin in uncertain environments using predictive hebbian learning. Nature 377(6551):725\u2013728","journal-title":"Nature"},{"key":"142_CR9126","unstructured":"Pomerleau D (1989) Alvinn: an autonomous land vehicle in a neural network. In: NIPS 1, Denver"},{"key":"142_CR9127","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936","volume-title":"Maximum margin planning","author":"N Ratliff","year":"2006","unstructured":"Ratliff N, Bagnell J, Zinkevich M (2006) Maximum margin planning. In: Proceedings of ICML, Pittsburgh"},{"key":"142_CR9128","first-page":"1153","volume":"19","author":"N Ratliff","year":"2007","unstructured":"Ratliff N, Bradley D, Bagnell J, Chestnutt J (2007) Boosting structured prediction for imitation learning. Neural Inf Process Syst 19:1153\u20131160","journal-title":"Neural Inf Process Syst"},{"key":"142_CR9129","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-247-2.50055-3","volume-title":"Learning to fly","author":"C Sammut","year":"1992","unstructured":"Sammut C, Hurst S, Kedzier D, Michie D (1992) Learning to fly. In: Proceedings of ICML, Aberdeen"},{"key":"142_CR9130","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1177\/105971239700600103","volume":"6","author":"NA Schmajuk","year":"1997","unstructured":"Schmajuk NA, Zanutto BS (1997) Escape, avoidance, and imitation. Adapt Behav 6:63\u2013129","journal-title":"Adapt Behav"},{"key":"142_CR9131","unstructured":"Taskar B, Guestrin C, Koller D (2003) Max-margin markov networks. In: Neural information processing systems conference (NIPS03), Vancouver"},{"key":"142_CR9132","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1177\/105971239700500302","volume":"5","author":"DS Touretzky","year":"1997","unstructured":"Touretzky DS, Saksida LM (1997) Operant conditioning in skinnerbots. Adapt Behav 5:219\u201347","journal-title":"Adapt Behav"},{"key":"142_CR9133","unstructured":"Watkins CJ (1989) Models of delayed reinforcement learning. Ph.D. thesis, Psychology Department, Cambridge University"}],"container-title":["Encyclopedia of Machine Learning and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4899-7687-1_142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T14:54:02Z","timestamp":1791816842000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4899-7687-1_142"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9781489976857","9781489976871"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-1-4899-7687-1_142","relation":{},"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"14 April 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}