{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:43:03Z","timestamp":1791481383518,"version":"4.3.4"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/icra.2017.7989043","type":"proceedings-article","created":{"date-parts":[[2017,7,25]],"date-time":"2017-07-25T17:44:28Z","timestamp":1501004668000},"page":"336-343","source":"Crossref","is-referenced-by-count":33,"title":["Learning from the hindsight plan \u2014 Episodic MPC improvement"],"prefix":"10.1109","author":[{"given":"Aviv","family":"Tamar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Garrett","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref32","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"AISTATS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"ref30","article-title":"Theano: A Python framework for fast computation of mathematical expressions","volume":"abs","year":"0","journal-title":"T development team"},{"key":"ref36","author":"pan","year":"2016","journal-title":"Adaptive probabilistic trajectory optimization via efficient approximate inference"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487174"},{"key":"ref34","author":"finn","year":"2016","journal-title":"Guided policy search code implementation"},{"key":"ref10","first-page":"73","article-title":"Infinite-horizon model predictive control for periodic tasks with contacts","author":"erez","year":"2012","journal-title":"Robotics Science and Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614995"},{"key":"ref12","author":"moore","year":"2000","journal-title":"Iterative Learning Control"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/002071700405905"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2006.1636313"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2009.09.006"},{"key":"ref16","author":"rosolia","year":"2016","journal-title":"Learning model predictive control for iterative tasks"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225036"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2000.912059"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1137\/0326056","article-title":"Maximum likelihood estimation of discrete control processes","volume":"26","author":"rust","year":"1988","journal-title":"SIAM Journal on Control and Optimization"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38253-6_3"},{"key":"ref27","article-title":"Value iteration networks","volume":"abs 1602 2867","author":"tamar","year":"2016","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315483"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759592"},{"key":"ref29","author":"anderson","year":"2007","journal-title":"Optimal control linear quadratic methods Courier Corporation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref7","first-page":"1181","article-title":"The dependence of effective planning horizon on model accuracy","author":"jiang","year":"2015","journal-title":"AAMAS International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029990"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1016\/S0005-1098(98)00073-9","article-title":"A quasi-infinite horizon nonlinear model predictive control scheme with guaranteed stability","volume":"34","author":"chen","year":"1998","journal-title":"Automatica"},{"key":"ref1","author":"camacho","year":"2013","journal-title":"Model Predictive Control"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref22","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"NIPS"},{"key":"ref21","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"ICML"},{"key":"ref24","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2007","journal-title":"NIPS"},{"key":"ref23","author":"\u00e5str\u00f6m","year":"2013","journal-title":"Adaptive control Courier Corporation"},{"key":"ref26","first-page":"3528","article-title":"Gradient estimation using stochastic computation graphs","author":"schulman","year":"2015","journal-title":"NIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"}],"event":{"name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","location":"Singapore, Singapore","start":{"date-parts":[[2017,5,29]]},"end":{"date-parts":[[2017,6,3]]}},"container-title":["2017 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7960754\/7988677\/07989043.pdf?arnumber=7989043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T12:10:05Z","timestamp":1569931805000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7989043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra.2017.7989043","relation":{},"subject":[],"published":{"date-parts":[[2017,5]]}}}