{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:44:32Z","timestamp":1729676672623,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/cdc.2014.7040160","type":"proceedings-article","created":{"date-parts":[[2015,2,17]],"date-time":"2015-02-17T14:53:59Z","timestamp":1424184839000},"page":"4938-4945","source":"Crossref","is-referenced-by-count":3,"title":["Unsupervised inverse reinforcement learning with noisy data"],"prefix":"10.1109","author":[{"given":"Amit","family":"Surana","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74949-3_13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2000.10474879"},{"key":"ref30","first-page":"639","article-title":"A constructive definition of Dirichlet priors","volume":"4","author":"sethuraman","year":"1994","journal-title":"Statistica Sinica"},{"key":"ref10","first-page":"663","article-title":"Algorithms for Inverse Reinforcement Learning","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390286"},{"key":"ref13","first-page":"1433","article-title":"Maximum Entropy Inverse Reinforcement Learning","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref14","first-page":"295","article-title":"Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods","author":"neu","year":"2007","journal-title":"VAI"},{"key":"ref15","first-page":"2586","article-title":"Bayesian Inverse Reinforcement Learning","author":"ramachandran","year":"2007","journal-title":"IJCAI"},{"key":"ref16","first-page":"1989","article-title":"MAP Inference for Bayesian Inverse Reinforcement Learning","author":"choi","year":"2011","journal-title":"NIPS"},{"key":"ref17","first-page":"691","article-title":"Inverse Reinforcement Learning in Partially Observable Envi-ronments","volume":"12","author":"choi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","first-page":"314","article-title":"Nonparametric Bayesian Inverse Reinforcement Learning for Multiple Reward Functions","author":"choi","year":"2012","journal-title":"NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1214\/08-BA326"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2011.08.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-008-0132-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/00949659908811984"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587510"},{"key":"ref6","first-page":"439","article-title":"A streakline representation of flow in crowded scenes","author":"mehran","year":"2010","journal-title":"European Conference on Computer Vision"},{"article-title":"Bayesian Nonparametric Learning of Complex Dynamical Phenomena","year":"2009","author":"fox","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206641"},{"key":"ref8","first-page":"201","article-title":"Activity Forecasting","author":"kitani","year":"2012","journal-title":"ECCV"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.176"},{"key":"ref9","article-title":"Bayesian N onparametric Inverse Reinforcement Learning for Switched Markov Decision Processes","author":"surana","year":"2014","journal-title":"ICMLA"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760916"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1198\/016214502753479464"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/s10994-009-5110-1","article-title":"Time parsers by inverse reinforcement learning","volume":"77","author":"neu","year":"2009","journal-title":"Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225241"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020281327116"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(95)01770-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008938201645"}],"event":{"name":"2014 IEEE 53rd Annual Conference on Decision and Control (CDC)","start":{"date-parts":[[2014,12,15]]},"location":"Los Angeles, CA, USA","end":{"date-parts":[[2014,12,17]]}},"container-title":["53rd IEEE Conference on Decision and Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7027307\/7039338\/07040160.pdf?arnumber=7040160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T20:47:06Z","timestamp":1651265226000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7040160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/cdc.2014.7040160","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}