{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T20:38:18Z","timestamp":1776458298226,"version":"3.51.2"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["MSIT2020R1C1C1009766"],"award-info":[{"award-number":["MSIT2020R1C1C1009766"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["MSIT2021R1A4A2001824"],"award-info":[{"award-number":["MSIT2021R1A4A2001824"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Information and Communications Technology Planning and Evaluation","award":["MSIT2020-0-00857"],"award-info":[{"award-number":["MSIT2020-0-00857"]}]},{"name":"Information and Communications Technology Planning and Evaluation","award":["MSIT2022-0-00480"],"award-info":[{"award-number":["MSIT2022-0-00480"]}]},{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/lra.2022.3191234","type":"journal-article","created":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T19:32:33Z","timestamp":1657913553000},"page":"10065-10072","source":"Crossref","is-referenced-by-count":17,"title":["Infusing Model Predictive Control Into Meta-Reinforcement Learning for Mobile Robots in Dynamic Environments"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0131-5445","authenticated-orcid":false,"given":"Jaeuk","family":"Shin","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Automation and Systems Research Institute, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8252-1966","authenticated-orcid":false,"given":"Astghik","family":"Hakobyan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Automation and Systems Research Institute, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7022-0592","authenticated-orcid":false,"given":"Mingyu","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Automation and Systems Research Institute, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6293-3939","authenticated-orcid":false,"given":"Yeoneung","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Automation and Systems Research Institute, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0204-4213","authenticated-orcid":false,"given":"Gihun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Automation and Systems Research Institute, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5887-6169","authenticated-orcid":false,"given":"Insoon","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Automation and Systems Research Institute, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref2","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref3","article-title":"A simple neural attentive meta-learner","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mishra","year":"2018"},{"key":"ref4","article-title":"ProMP: Proximal meta-policy search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rothfuss","year":"2018"},{"key":"ref5","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly","year":"2019"},{"key":"ref6","article-title":"VariBAD: A very good method for bayes-adaptive deep RL via meta-learning","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Zintgraf","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3170582"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926677"},{"key":"ref11","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nagabandi","year":"2018"},{"key":"ref12","first-page":"642","article-title":"Meta reinforcement learning with latent variable Gaussian processes","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Smundsson","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341462"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28650-9_4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4266(02)00271-6"},{"key":"ref16","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref17","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende","year":"2014"},{"key":"ref18","article-title":"Deep variational information bottleneck","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Alemi","year":"2017"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191234"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2929980"},{"key":"ref22","volume-title":"Numerical Optimization","author":"Nocedal","year":"2006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2022.3200156"},{"key":"ref24","volume-title":"Vehicle Dynamics and Control","author":"Rajamani","year":"2011"},{"key":"ref25","article-title":"FORCES professional","volume-title":"Embotech AG","author":"Domahidi","year":"20142019"},{"key":"ref26","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref27","article-title":"Meta-reinforcement learning robust to distributional shift via model identification and experience relabeling","author":"Mendonca","year":"2020"},{"key":"ref28","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chua","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2007.01089.x"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9831196\/09830833.pdf?arnumber=9830833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T07:33:02Z","timestamp":1706772782000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9830833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":29,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3191234","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}