{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:28:33Z","timestamp":1730204913291,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SHF-2048094,CNS-1932620,CNS-2039087,FMitF-1837131,CCF-SHF-1932620"],"award-info":[{"award-number":["SHF-2048094,CNS-1932620,CNS-2039087,FMitF-1837131,CCF-SHF-1932620"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383295","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:36Z","timestamp":1705671516000},"page":"5376-5383","source":"Crossref","is-referenced-by-count":0,"title":["Convex Optimization-Based Policy Adaptation to Compensate for Distributional Shifts"],"prefix":"10.1109","author":[{"given":"Navid","family":"Hashemi","sequence":"first","affiliation":[{"name":"University of Southern California,Thomas Lord, Department of Computer Science,Los Angeles,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Ruths","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas,Department of Mechanical and System Engineering,Dallas,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jyotirmoy V.","family":"Deshmukh","sequence":"additional","affiliation":[{"name":"University of Southern California,Thomas Lord, Department of Computer Science,Los Angeles,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Robust and optimal control.","year":"1996","author":"Khalil","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3046193"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8205959"},{"key":"ref4","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"Christiano","year":"2016","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"281","article-title":"Mutual alignment transfer learning","volume-title":"Conference on Robot Learning","author":"Wulfmeier","year":"2017"},{"key":"ref6","article-title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","author":"Eysenbach","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"2817","article-title":"Robust adversar-ial reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pinto","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref9","first-page":"5082","article-title":"Fingerprint policy optimi-sation for robust reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Paul","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref11","volume-title":"Stochastic optimal control: the discrete-time case.","volume":"5","author":"Bertsekas","year":"1996"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"volume-title":"Introduction to machine learning.","year":"2020","author":"Alpaydin","key":"ref14"},{"key":"ref15","article-title":"Deep rein-forcement learning in a handful of trials using probabilistic dynamics models","author":"Chua","year":"2018","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1063\/1.3034123"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029310"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482752"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-07210-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488968"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3046193"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383295.pdf?arnumber=10383295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:22:40Z","timestamp":1706008960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383295","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}