{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:36:10Z","timestamp":1761060970572,"version":"3.38.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8967966","type":"proceedings-article","created":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T04:53:51Z","timestamp":1580446431000},"page":"990-996","source":"Crossref","is-referenced-by-count":2,"title":["Fast and Safe Policy Adaptation via Alignment-based Transfer"],"prefix":"10.1109","author":[{"given":"Jigang","family":"Kim","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Mechanical and Aerospace Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungwon","family":"Choi","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Mechanical and Aerospace Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H. Jin","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Mechanical and Aerospace Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref11","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref12","first-page":"1087","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref14","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","author":"garcia","year":"2015","journal-title":"Journal of Machine Learning Research 16 1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989680"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_455"},{"key":"ref18","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461218"},{"key":"ref4","article-title":"Unsupervised cross-domain transfer in policy gradient reinforcement learning via manifold alignment","author":"ammar","year":"2015","journal-title":"Proc Of AAAI"},{"key":"ref3","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref6","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"},{"key":"ref5","first-page":"12","article-title":"Robot learning from demonstration","volume":"97","author":"atkeson","year":"1997","journal-title":"ICML"},{"key":"ref8","first-page":"16","article-title":"Introduction to inverse kinematics with jacobian transpose, pseudoinverse and damped least squares methods","author":"buss","year":"2004","journal-title":"IEEE Journal of Robotics and Automation 17 1-19"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6706721"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157815"},{"key":"ref9","first-page":"8103","article-title":"A Lyapunov-based Approach to Safe Reinforcement Learning","author":"chow","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref20","first-page":"529","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature 518 7540"},{"key":"ref22","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref23","article-title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","author":"schulman","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08967966.pdf?arnumber=8967966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T18:43:13Z","timestamp":1741200193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967966","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}