{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:03:14Z","timestamp":1784736194333,"version":"3.55.0"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Scalable Collaborative Human-Robot Learning"},{"name":"NSF National Robotics Initiative","award":["1734633"],"award-info":[{"award-number":["1734633"]}]},{"name":"Google and Toyota Research Institute"},{"name":"NSF GRFP"},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-311"],"award-info":[{"award-number":["N00014-311"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/lra.2020.2976272","type":"journal-article","created":{"date-parts":[[2020,2,26]],"date-time":"2020-02-26T21:04:59Z","timestamp":1582751099000},"page":"3612-3619","source":"Crossref","is-referenced-by-count":52,"title":["Safety Augmented Value Estimation From Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1841-5071","authenticated-orcid":false,"given":"Brijen","family":"Thananjeyan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-7850","authenticated-orcid":false,"given":"Ashwin","family":"Balakrishna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ugo","family":"Rosolia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rowan","family":"McAllister","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph E.","family":"Gonzalez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8919-6430","authenticated-orcid":false,"given":"Francesco","family":"Borrelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6747-9499","authenticated-orcid":false,"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907809"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061759"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030270"},{"key":"ref34","first-page":"2074","article-title":"Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations","author":"berg","year":"0","journal-title":"Proc IEEE Int Conf Robot Autom"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2011.11.006"},{"key":"ref11","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","author":"lowrey","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref13","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","first-page":"3223","author":"hester","year":"0","journal-title":"Proc 22nd AAAI Conf Artif Intell"},{"key":"ref15","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref17","first-page":"3036","article-title":"The gap between model-based and model-free methods on the linear quadratic regulator: An asymptotic viewpoint","author":"tu","year":"2019","journal-title":"Proc Conf Learn Theory"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1993.291936"},{"key":"ref19","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume":"97","author":"brown","year":"2019","journal-title":"Proceedings 36th Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2753460"},{"key":"ref4","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","first-page":"233","article-title":"Robustness and risk-sensitivity in markov decision processes","volume":"1","author":"osogami","year":"0","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963748"},{"key":"ref6","article-title":"On-policy robot imitation learning from a converging supervisor","author":"balakrishna","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619268"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"ref8","article-title":"Concrete problems in AI safety","author":"amodei","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759592"},{"key":"ref2","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460583"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2006.1636313"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430770"},{"key":"ref21","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref24","first-page":"22","article-title":"Constrained policy optimization","volume":"70","author":"achiam","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref23","first-page":"1451","article-title":"Safe exploration in markov decision processes","author":"moldovan","year":"0","journal-title":"Proc 29th Int Conf Machine Learn"},{"key":"ref26","first-page":"3131","article-title":"Risk aversion in markov decision processes via near optimal chernoff bounds","author":"moldovan","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref25","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8932682\/09013084.pdf?arnumber=9013084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:32:35Z","timestamp":1651080755000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9013084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":34,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2976272","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}