{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T11:32:37Z","timestamp":1768735957462,"version":"3.49.0"},"reference-count":35,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["2133656"],"award-info":[{"award-number":["2133656"]}]},{"name":"NSF","award":["1830639"],"award-info":[{"award-number":["1830639"]}]},{"name":"AI Institute Planning","award":["2020289"],"award-info":[{"award-number":["2020289"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/lra.2022.3169309","type":"journal-article","created":{"date-parts":[[2022,4,21]],"date-time":"2022-04-21T19:33:55Z","timestamp":1650569635000},"page":"6574-6581","source":"Crossref","is-referenced-by-count":27,"title":["Improving the Robustness of Reinforcement Learning Policies With ${\\mathcal {L}_{1}}$ Adaptive Control"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7911-1496","authenticated-orcid":false,"given":"Yikun","family":"Cheng","sequence":"first","affiliation":[{"name":"Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9349-1125","authenticated-orcid":false,"given":"Pan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3935-7205","authenticated-orcid":false,"given":"Fanxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"}]},{"given":"Daniel J.","family":"Block","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3850-1073","authenticated-orcid":false,"given":"Naira","family":"Hovakimyan","sequence":"additional","affiliation":[{"name":"Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3153712"},{"key":"ref32","article-title":"Improving the robustness of reinforcement learning policies with $\\mathcal {L}_{1}$ adaptive control","author":"cheng","year":"2021"},{"key":"ref31","first-page":"2021","article-title":"Robust adaptive control of linear parameter-varying systems with unmatched uncertainties","author":"zhao","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303829"},{"key":"ref35","first-page":"1907","article-title":"Probabilistic differential dynamic programming","author":"pan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"829","article-title":"Learning complex neural network policies with trajectory optimization","author":"levine","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","author":"zhou","year":"1998","journal-title":"Essentials of Robust Control"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9028930"},{"key":"ref12","article-title":"MRAC-RL: A framework for on-line policy adaptation under parametric model uncertainty","author":"guha","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719376"},{"key":"ref14","first-page":"7661","article-title":"$\\mathcal {L}_{1}$-adaptive MPPI architecture for robust and agile control of multirotors","author":"pravitra","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref15","first-page":"826","article-title":"$\\mathcal {L}_{1}$-$\\mathcal {GP}$: $\\mathcal {L}_{1}$ adaptive control with Bayesian learning","author":"gahlawat","year":"0","journal-title":"Proc 2nd Annu Conf Learn Dyn Control"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303957"},{"key":"ref17","first-page":"1027","article-title":"Contraction $\\mathcal {L}_{1}$ adaptive control using Gaussian processes","author":"gahlawat","year":"0","journal-title":"Proc 3rd Conf Learn Dyn Control"},{"key":"ref18","first-page":"112 6","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref19","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref27","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2942989"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref8","article-title":"Wasserstein robust reinforcement learning","author":"abdullah","year":"2019"},{"key":"ref7","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","first-page":"133","article-title":"Deep drone racing: Learning agile flight in dynamic environments","author":"kaufmann","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref9","first-page":"8093","article-title":"Overfitting in adversarially robust deep learning","author":"rice","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","article-title":"Deep online learning via meta-learning: Continual adaptation for model-based RL","author":"nagabandi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","first-page":"6429","article-title":"Task-agnostic online reinforcement learning with an infinite mixture of Gaussian processes","author":"xu","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref21","article-title":"Meta reinforcement learning with latent variable Gaussian processes","author":"s\u00e6mundsson","year":"0","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2478397"},{"key":"ref23","author":"ioannou","year":"2012","journal-title":"Robust Adaptive Control"},{"key":"ref26","first-page":"781","article-title":"Probabilistic safety constraints for learned high relative degree system dynamics","author":"khojasteh","year":"0","journal-title":"Proc Annu Conf Learn Dyn Control"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.9746\/jcmsi.13.165"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/9750005\/9761728-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9750005\/09761728.pdf?arnumber=9761728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T20:32:16Z","timestamp":1655152336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9761728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":35,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3169309","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}