{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T15:37:55Z","timestamp":1769182675531,"version":"3.49.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"European Project (KoroiBot)","award":["FP7-ICT-2013-10\/611909"],"award-info":[{"award-number":["FP7-ICT-2013-10\/611909"]}]},{"name":"ROBOTIS which provided motors for Leo"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/lra.2018.2800106","type":"journal-article","created":{"date-parts":[[2018,1,31]],"date-time":"2018-01-31T19:19:30Z","timestamp":1517426370000},"page":"2471-2477","source":"Crossref","is-referenced-by-count":34,"title":["Model-Plant Mismatch Compensation Using Reinforcement Learning"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-1016","authenticated-orcid":false,"given":"Ivan","family":"Koryakovskiy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4598-7833","authenticated-orcid":false,"given":"Manuel","family":"Kudruss","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0305-398X","authenticated-orcid":false,"given":"Heike","family":"Vallery","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-8598","authenticated-orcid":false,"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9069-2378","authenticated-orcid":false,"given":"Wouter","family":"Caarls","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref11","article-title":"Data-efficient reinforcement learning with probabilistic model predictive\n control","author":"kamthe","year":"2017","journal-title":"arXiv 1706 06491"},{"key":"ref12","first-page":"2829","article-title":"Continuous deep Q-learning with model-based\n acceleration","author":"gu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","first-page":"365","article-title":"Feedback-error-learning neural network for supervised motor\n learning","volume":"6","author":"kawato","year":"1990","journal-title":"Adv Neural Comput"},{"key":"ref14","article-title":"Transfer from simulation to real world through\n learning deep inverse dynamics model","author":"christiano","year":"2016","journal-title":"arXiv 1610 03518"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942746"},{"key":"ref16","first-page":"2620","article-title":"Reducing hardware experiments for model learning and policy optimization","author":"ha","year":"0","journal-title":"Proc IEEE Int Conf Robot Autom"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206343"},{"key":"ref18","article-title":"EPOpt: Learning robust neural network\n policies using model ensembles","author":"rajeswaran","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref28","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3182\/20140824-6-ZA-1003.02511"},{"key":"ref27","article-title":"Combining multi-level real-time iterations of nonlinear model\n predictive control to realize squatting motions on Leo","author":"kudruss","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2010.07.012"},{"key":"ref6","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","first-page":"1181","article-title":"The dependence of effective planning\n horizon on model accuracy","author":"jiang","year":"0","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1998.703301"},{"key":"ref8","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.02.006"},{"key":"ref9","article-title":"High-dimensional continuous control using generalized advantage\n estimation","author":"schulman","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref1","article-title":"Reinforcement learning on autonomous humanoid robots","author":"schuitema","year":"2012"},{"key":"ref20","first-page":"1607","article-title":"Relative\n entropy policy search","author":"peters","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref21","first-page":"1","article-title":"Guided policy search","author":"levine","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","first-page":"143","article-title":"Safe exploration for\n reinforcement learning","author":"hans","year":"0","journal-title":"Proc Eur Symp Artif Neural Netw"},{"key":"ref23","first-page":"1711","article-title":"Safe exploration in Markov decision processes","author":"moldovan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718935.ch1"},{"key":"ref25","article-title":"A general safety framework for learning-based control in uncertain robotic systems","author":"fisac","year":"2017","journal-title":"arXiv 1705 01292"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8302435\/08276249.pdf?arnumber=8276249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T07:13:59Z","timestamp":1643181239000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8276249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":29,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2018.2800106","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}