{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T07:53:05Z","timestamp":1794383585970,"version":"4.9.0"},"publisher-location":"Boston, MA","reference-count":11,"publisher":"Springer US","isbn-type":[{"value":"9780387307688","type":"print"},{"value":"9780387301648","type":"electronic"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-0-387-30164-8_417","type":"book-chapter","created":{"date-parts":[[2010,12,29]],"date-time":"2010-12-29T12:31:37Z","timestamp":1293625897000},"page":"554-558","source":"Crossref","is-referenced-by-count":16,"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","reference":[{"key":"417_CR1_417","volume-title":"Proceedings of ICML","author":"P Abbeel","year":"2004","unstructured":"Abbeel, P., & Ng, A. Y. (2004). Apprenticeship learning via inverse reinforcement learning. In Proceedings of ICML, Banff, Alberta, Canada."},{"key":"417_CR2_417","volume-title":"Neural Information Processing Systems 7","author":"K Doya","year":"1995","unstructured":"Doya, K., & Sejnowski, T. (1995). A novel reinforcement model of birdsong vocalization learning. In Neural Information Processing Systems 7. Cambridge, MA: MIT\u00a0Press."},{"issue":"6551","key":"417_CR3_417","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1038\/377725a0","volume":"377","author":"PR Montague","year":"1995","unstructured":"Montague, P. R., Dayan, P., Person, C., & Sejnowski, T. J. (1995). Bee foraging in uncertain environments using predictive hebbian learning. Nature, 377(6551), 725\u2013728.","journal-title":"Nature"},{"key":"417_CR4_417","volume-title":"NIPS 1","author":"D Pomerleau","year":"1989","unstructured":"Pomerleau, D. (1989). ALVINN: An autonomous land vehicle in a neural network. In NIPS 1. San Francisco, CA: Morgan Kaufmann."},{"key":"417_CR5_417","volume-title":"Proceedings of ICML","author":"N Ratliff","year":"2006","unstructured":"Ratliff, N., Bagnell, J., & Zinkevich, M. (2006). Maximum margin planning. In Proceedings of ICML, Pittsburgh, Pennsylvania."},{"key":"417_CR6_417","volume-title":"Neural Information Processing Systems 19","author":"N Ratliff","year":"2007","unstructured":"Ratliff, N., Bradley, D., Bagnell, J., & Chestnutt, J. (2007). Boosting structured prediction for imitation learning. In Neural Information Processing Systems 19. Cambridge, MA: MIT\u00a0Press."},{"key":"417_CR7_417","volume-title":"Proceedings of ICML","author":"C Sammut","year":"1992","unstructured":"Sammut, C., Hurst, S., Kedzier, D., & Michie, D. (1992). Learning to fly. In Proceedings of ICML. Aberdeen, Scotland, UK."},{"key":"417_CR8_417","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1177\/105971239700600103","volume":"6","author":"NA Schmajuk","year":"1997","unstructured":"Schmajuk, N. A., & Zanutto, B. S. (1997). Escape, avoidance, and imitation. Adaptive Behavior, 6,\u00a063\u2013129.","journal-title":"Adaptive Behavior"},{"key":"417_CR9_417","volume-title":"Neural Information Processing Systems Conference (NIPS03)","author":"B Taskar","year":"2003","unstructured":"Taskar, B., Guestrin, C., & Koller, D. (2003). Max-margin Markov networks. In Neural Information Processing Systems Conference (NIPS03), Vancouver, Canada."},{"key":"417_CR10_417","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1177\/105971239700500302","volume":"5","author":"DS Touretzky","year":"1997","unstructured":"Touretzky, D. S., & Saksida, L. M. (1997). Operant conditioning in skinnerbots. Adaptive Behavior, 5, 219\u2013247.","journal-title":"Adaptive Behavior"},{"key":"417_CR11_417","unstructured":"Watkins, C. J. (1989). Models of delayed reinforcement learning. PhD thesis, Psychology Department, Cambridge University."}],"container-title":["Encyclopedia of Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-0-387-30164-8_417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T21:36:43Z","timestamp":1703194603000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-0-387-30164-8_417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9780387307688","9780387301648"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-0-387-30164-8_417","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-0-387-30164-8","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2011]]}}}