{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:55:57Z","timestamp":1729637757424,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9562051","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"10595-10602","source":"Crossref","is-referenced-by-count":0,"title":["Protective Policy Transfer"],"prefix":"10.1109","author":[{"given":"Wenhao","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. Karen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Greg","family":"Turk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref39"},{"article-title":"Learning to be safe: Deep rl with a safety critic","year":"2020","author":"srinivasan","key":"ref38"},{"article-title":"Projection-based constrained policy optimization","year":"0","author":"yang","key":"ref33"},{"article-title":"Leave no trace: Learning to reset for safe and autonomous reinforcement learning","year":"2017","author":"eysenbach","key":"ref32"},{"article-title":"Safety-guided deep reinforcement learning via online gaussian process estimation","year":"2019","author":"fan","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487170"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206246"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2006.321323"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1041648"},{"key":"ref34","first-page":"2761","article-title":"Multiple contact planning for minimizing damage of humanoid falls","author":"ha","year":"2015","journal-title":"2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref10","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207344"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197000"},{"article-title":"Compositional transfer in hierarchical reinforcement learning","year":"2019","author":"wulfmeier","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968053"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"article-title":"Solving rubik’s cube with a robot hand","year":"2019","author":"akkaya","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.031"},{"key":"ref18","first-page":"317","article-title":"Learning locomotion skills for cassie: Iterative design and sim-to-real","volume":"100","author":"xie","year":"0"},{"key":"ref19","first-page":"1","article-title":"Sim-to-real transfer of robotic control with dynamics randomization","author":"peng","year":"2018","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"article-title":"First order optimization in policy space for constrained deep reinforcement learning","year":"2020","author":"zhang","key":"ref28"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2020.XVI.040","article-title":"Deep drone acrobatics","author":"kaufmann","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"article-title":"Learning agile robotic locomotion skills by imitating animals","year":"2020","author":"peng","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11436"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23461-8_9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"article-title":"Reward constrained policy optimization","year":"0","author":"tessler","key":"ref8"},{"key":"ref7","first-page":"22","article-title":"Constrained policy optimization","volume":"70","author":"achiam","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"article-title":"Learning fast adaptation with meta strategy optimization","year":"2019","author":"yu","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"article-title":"Single episode policy transfer in reinforcement learning","year":"0","author":"yang","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","first-page":"143","article-title":"Safe exploration for reinforcement learning","author":"hans","year":"2008","journal-title":"ESANN"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00500"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3761"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.02.003"},{"article-title":"Policy transfer with strategy optimization","year":"0","author":"yu","key":"ref43"},{"key":"ref25","first-page":"803","article-title":"Lyapunov design for safe reinforcement learning","volume":"3","author":"perkins","year":"2002","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09562051.pdf?arnumber=9562051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:53:41Z","timestamp":1673564021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9562051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9562051","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}