{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:18:50Z","timestamp":1766067530789,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100019266","name":"Korea Medical Device Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Science and ICT"},{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Health & Welfare"},{"DOI":"10.13039\/501100003569","name":"Ministry of Food and Drug Safety","doi-asserted-by":"publisher","award":["202013D05"],"award-info":[{"award-number":["202013D05"]}],"id":[{"id":"10.13039\/501100003569","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/lra.2022.3173039","type":"journal-article","created":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T19:37:55Z","timestamp":1651865875000},"page":"6606-6613","source":"Crossref","is-referenced-by-count":9,"title":["Automating Reinforcement Learning With Example-Based Resets"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3381-5241","authenticated-orcid":false,"given":"Jigang","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8410-4568","authenticated-orcid":false,"given":"J. hyeon","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4105-4422","authenticated-orcid":false,"given":"Daesol","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6819-1136","authenticated-orcid":false,"given":"H. Jin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202141"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.053"},{"key":"ref8","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Kalashnikov","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref10","first-page":"1110","article-title":"Learning to walk in the real world with minimal human effort","volume-title":"Proc. Conf. Robot Learn. (PMLR)","author":"Ha","year":"2021"},{"key":"ref11","first-page":"4999","article-title":"Continual learning of control primitives: Skill discovery via reset-games","volume":"33","author":"Xu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref12","article-title":"The ingredients of real world robotic reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref14","first-page":"18474","article-title":"Autonomous reinforcement learning via subgoal curricula","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sharma","year":"2021"},{"key":"ref15","first-page":"14783","article-title":"Rewriting history with inverse rl: Hindsight inference for policy improvement","volume":"33","author":"Eysenbach","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354297"},{"key":"ref17","article-title":"Leave no trace: Learning to reset for safe and autonomous reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref20","article-title":"Prioritized experience replay","volume-title":"4th Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref21","article-title":"Learning the arrow of time for problems in reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rahaman","year":"2020"},{"key":"ref22","first-page":"1898","article-title":"There is no turning back: A self-supervised approach for reversibility-aware reinforcement learning","volume":"34","author":"Grinsztajn","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref23","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","volume":"78","author":"Florensa","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196733"},{"key":"ref25","first-page":"8538","article-title":"Variational inverse control with events: A general framework for data-driven reward definition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fu","year":"2018"},{"key":"ref26","first-page":"11541","article-title":"Replacing rewards with examples: Example-based policy search via recursive classification","volume":"34","author":"Eysenbach","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Lillicrap","year":"2016"},{"key":"ref28","first-page":"8617","article-title":"Randomized prior functions for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Osband","year":"2018"},{"article-title":"Openai gym","year":"2016","author":"Brockman","key":"ref29"},{"key":"ref30","article-title":"DeepMind control suite","volume-title":"DeepMind, Tech. Rep","author":"Tassa","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9750005\/09770380.pdf?arnumber=9770380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:37:47Z","timestamp":1705963067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9770380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":30,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3173039","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}