{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:46:11Z","timestamp":1743079571229,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319712451"},{"type":"electronic","value":"9783319712468"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-71246-8_23","type":"book-chapter","created":{"date-parts":[[2017,12,29]],"date-time":"2017-12-29T09:03:20Z","timestamp":1514538200000},"page":"373-388","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Generalized Inverse Reinforcement Learning with Linearly Solvable MDP"],"prefix":"10.1007","author":[{"given":"Masahiro","family":"Kohjima","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsushi","family":"Matsubayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Sawada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,12,30]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Coates, A., Quigley, M., Ng, A.Y.: An application of reinforcement learning to aerobatic helicopter flight. In: NIPS, pp. 1\u20138 (2007)","DOI":"10.7551\/mitpress\/7503.003.0006"},{"key":"23_CR2","unstructured":"Ziebart, B.D., Maas, A.L., Bagnell, J.A., Dey, A.K.: Maximum entropy inverse reinforcement learning. In: AAAI, pp. 1433\u20131438 (2008)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Song, X., Zhang, Q., Sekimoto, Y., Shibasaki, R.: Intelligent system for urban emergency management during large-scale disaster. In: AAAI, pp. 458\u2013464 (2014)","DOI":"10.1609\/aaai.v28i1.8758"},{"issue":"2\u20133","key":"23_CR4","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. Mach. Learn. 77(2\u20133), 303\u2013337 (2009)","journal-title":"Mach. Learn."},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Todorov, E.: Linearly-solvable Markov decision problems. In: NIPS, pp. 1369\u20131376 (2006)","DOI":"10.7551\/mitpress\/7503.003.0176"},{"key":"23_CR6","unstructured":"Dvijotham, K., Todorov, E.: Inverse optimal control with linearly-solvable MDPs. In: ICML, pp. 335\u2013342 (2010)"},{"key":"23_CR7","unstructured":"Ng, A.Y., Russell, S.: Algorithms for inverse reinforcement learning. In: ICML, pp. 663\u2013670 (2000)"},{"key":"23_CR8","unstructured":"Makino, T., Takeuchi, J.: Apprenticeship learning for model parameters of partially observable environments. In: ICML, pp. 1495\u20131502 (2012)"},{"key":"23_CR9","unstructured":"Ramachandran, D., Amir, E.: Bayesian inverse reinforcement learning. In: IJCAI, pp. 2586\u20132591 (2007)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Rothkopf, C.A., Dimitrakakis, C.: Preference elicitation and inverse reinforcement learning. In: ECML PKDD, pp. 34\u201348 (2011)","DOI":"10.1007\/978-3-642-23808-6_3"},{"key":"23_CR11","unstructured":"Lazaric, A., Ghavamzadeh, M.: Bayesian multi-task reinforcement learning. In: ICML, pp. 599\u2013606 (2010)"},{"key":"23_CR12","unstructured":"Babes, M., Marivate, V., Subramanian, K., Littman, M.L.: Apprenticeship learning about multiple intentions. In: ICML, pp. 897\u2013904 (2011)"},{"key":"23_CR13","series-title":"Wiley Series in Probability and Statistics","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2005","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley Series in Probability and Statistics. Wiley, Hoboken (2005)"},{"key":"23_CR14","volume-title":"Asymptotic Statistics","author":"AW Van der Vaart","year":"2000","unstructured":"Van der Vaart, A.W.: Asymptotic Statistics. Cambridge University Press, Cambridge (2000)"},{"key":"23_CR15","unstructured":"Bishop, C.M., Svenskn, M.: Bayesian hierarchical mixtures of experts. In: UAI, pp. 57\u201364 (2002)"},{"issue":"2","key":"23_CR16","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1023\/A:1007665907178","volume":"37","author":"MI Jordan","year":"1999","unstructured":"Jordan, M.I., Ghahramani, Z., Jaakkola, T.S., Saul, L.K.: An introduction to variational methods for graphical models. Mach. Learn. 37(2), 183\u2013233 (1999)","journal-title":"Mach. Learn."},{"key":"23_CR17","unstructured":"Jaakkola, T., Jordan, M.I.: A variational approach to Bayesian logistic regression models and their extensions. In: AISTATS (1997)"},{"key":"23_CR18","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1214\/07-AOAS114","volume":"1","author":"DM Blei","year":"2007","unstructured":"Blei, D.M., Lafferty, J.D.: A correlated topic model of science. Ann. Appl. Stat. 1, 17\u201335 (2007)","journal-title":"Ann. Appl. Stat."},{"issue":"1","key":"23_CR19","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/BF00048682","volume":"44","author":"D B\u00f6hning","year":"1992","unstructured":"B\u00f6hning, D.: Multinomial logistic regression algorithm. Ann. Inst. Stat. Math. 44(1), 197\u2013200 (1992)","journal-title":"Ann. Inst. Stat. Math."},{"key":"23_CR20","unstructured":"Bouchard, G.: Efficient bounds for the softmax function and applications to approximate inference in hybrid models. In: NIPS 2007 Workshop for Approximate Bayesian Inference in Continuous\/Hybrid Systems (2007)"},{"key":"23_CR21","unstructured":"Jebara, T., Choromanska, A.: Majorization for CRFs and latent likelihoods. In: NIPS, pp. 557\u2013565 (2012)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Yuan, J., Zheng, Y., Zhang, C., Xie, W., Xie, X., Sun, G., Huang, Y.: T-drive: driving directions based on taxi trajectories. In: SIGSPATIAL, pp. 99\u2013108 (2010)","DOI":"10.1145\/1869790.1869807"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-71246-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T08:32:32Z","timestamp":1693384352000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-71246-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319712451","9783319712468"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-71246-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"30 December 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Skopje","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macedonia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2017.ijs.si\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}