{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:54:59Z","timestamp":1729626899650,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/ssci.2017.8280919","type":"proceedings-article","created":{"date-parts":[[2018,2,7]],"date-time":"2018-02-07T16:44:37Z","timestamp":1518021877000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Gradient-based minimization for multi-expert Inverse Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Davide","family":"Tateo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Pirotta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Bonarini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40988-2_1"},{"key":"ref11","first-page":"897","article-title":"Apprenticeship learning about multiple intentions","author":"babes","year":"2011","journal-title":"Proc ICML"},{"key":"ref12","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume":"51","author":"ramachandran","year":"2007","journal-title":"Proc IJCAI"},{"key":"ref13","first-page":"295","article-title":"Apprenticeship learning using inverse reinforcement learning and gradient methods","author":"neu","year":"2007","journal-title":"Proc UAI"},{"key":"ref14","first-page":"314","article-title":"Nonparametric bayesian inverse reinforcement learning for multiple reward functions","author":"choi","year":"2012","journal-title":"Proc NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29946-9_27"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"},{"journal-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","year":"2006","author":"bishop","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1137\/120887795"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09903-3_13"},{"key":"ref4","first-page":"3315","article-title":"Maximum entropy semi-supervised inverse reinforcement learning","author":"audiffren","year":"2015","journal-title":"Proc IJCAI"},{"key":"ref3","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"Proc AAAI"},{"key":"ref6","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with gaussian processes","author":"levine","year":"2011","journal-title":"Proc NIPS"},{"key":"ref5","first-page":"335","article-title":"Inverse optimal control with linearly-solvable mdps","author":"dvijotham","year":"2010","journal-title":"Proc ICML"},{"key":"ref8","first-page":"182","article-title":"Relative entropy inverse reinforcement learning","author":"boularias","year":"2011","journal-title":"Proc AISTATS"},{"key":"ref7","first-page":"1993","article-title":"Inverse reinforcement learning through policy gradient minimization","author":"pirotta","year":"2016","journal-title":"Proc AAAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","first-page":"1007","article-title":"Inverse reinforcement learning through structured classification","author":"klein","year":"2012","journal-title":"Proc NIPS"},{"key":"ref20","first-page":"262","article-title":"Analysis and improvement of policy gradient estimation","author":"zhao","year":"2011","journal-title":"Proc NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280673"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref24","first-page":"226","article-title":"Hierarchical policy gradient algorithms","author":"ghavamzadeh","year":"2003","journal-title":"Proc ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9132-0"}],"event":{"name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2017,11,27]]},"location":"Honolulu, HI","end":{"date-parts":[[2017,12,1]]}},"container-title":["2017 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8267146\/8280782\/08280919.pdf?arnumber=8280919","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T10:21:47Z","timestamp":1570702907000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8280919\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ssci.2017.8280919","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}