{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:15:46Z","timestamp":1774455346140,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":["IIS-2024775"],"award-info":[{"award-number":["IIS-2024775"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981913","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"9347-9354","source":"Crossref","is-referenced-by-count":13,"title":["Hybrid LMC: Hybrid Learning and Model-based Control for Wheeled Humanoid Robot via Ensemble Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Donghoon","family":"Baek","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amartya","family":"Purushottam","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joao","family":"Ramos","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363451"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aav4282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793792"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967935"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979625"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340967"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0020294018758527"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794360"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.098"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3100269"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341372"},{"key":"ref17","article-title":"Bayesian controller fusion: Leveraging control priors in deep reinforcement learning for robotics","author":"Rana","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3047787"},{"key":"ref20","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"Chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Advances in neural information processing systems","volume":"30","author":"Lakshminarayanan","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561368"},{"key":"ref25","first-page":"916","article-title":"Policies modulating trajectory generators","volume-title":"Conference on Robot Learning","author":"Iscen"},{"key":"ref26","article-title":"Accelerating reinforcement learning with learned skill priors","author":"Pertsch","year":"2020","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981913.pdf?arnumber=9981913","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:41:43Z","timestamp":1706758903000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981913\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981913","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}