{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:26:00Z","timestamp":1767338760638,"version":"3.40.3"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100007210","name":"RWTH Aachen University","doi-asserted-by":"publisher","award":["RWTH1205"],"award-info":[{"award-number":["RWTH1205"]}],"id":[{"id":"10.13039\/501100007210","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tro.2025.3539192","type":"journal-article","created":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T19:22:54Z","timestamp":1738783374000},"page":"2533-2548","source":"Crossref","is-referenced-by-count":1,"title":["Simulation-Aided Policy Tuning for Black-Box Robot Learning"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4461-4795","authenticated-orcid":false,"given":"Shiming","family":"He","sequence":"first","affiliation":[{"name":"School of Information and Electrical Engineering, Hangzhou City University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0005-0310","authenticated-orcid":false,"given":"Alexander","family":"von Rohr","sequence":"additional","affiliation":[{"name":"Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7340-2180","authenticated-orcid":false,"given":"Dominik","family":"Baumann","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7234-6460","authenticated-orcid":false,"given":"Ji","family":"Xiang","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2785-2487","authenticated-orcid":false,"given":"Sebastian","family":"Trimpe","sequence":"additional","affiliation":[{"name":"Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"article-title":"Solving rubik\u2019s cube with a robot hand","year":"2019","author":"OpenAI","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"ref7","first-page":"2616","article-title":"Probabilistic movement primitives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Paraschos","year":"2013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610040"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202137"},{"key":"ref10","first-page":"5496","article-title":"Scalable global optimization via local Bayesian optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Eriksson","year":"2019"},{"key":"ref11","first-page":"20708","article-title":"Local policy search with Bayesian optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Mller","year":"2021"},{"key":"ref12","first-page":"227","article-title":"Cautious Bayesian optimization for efficient and scalable policy search","volume-title":"Proc. Learn. Dyn. Control","author":"Frhlich","year":"2021"},{"key":"ref13","first-page":"493","article-title":"High-dimensional Bayesian optimization with sparse axis-aligned subspaces","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Eriksson","year":"2021"},{"key":"ref14","first-page":"13190","article-title":"Local Bayesian optimization via maximizing probability of descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen","year":"2022"},{"key":"ref15","first-page":"43347","article-title":"Are random decompositions all we need in high dimensional Bayesian optimisation?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ziomek","year":"2023"},{"key":"ref16","first-page":"334","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","volume-title":"Proc. Conf. Robot Learn.","author":"James","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref19","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gupta","year":"2017"},{"key":"ref20","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume-title":"Proc. Conf. Robot Learn.","author":"Rusu","year":"2017"},{"key":"ref21","first-page":"1558","article-title":"DIRL: Domain-invariant representation learning for sim-to-real transfer","volume-title":"Proc. Conf. Robot Learn.","author":"Tanwani","year":"2021"},{"key":"ref22","first-page":"1015","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srinivas","year":"2010"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487170"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487144"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812406"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304147"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967567"},{"key":"ref29","first-page":"1244","article-title":"Deep black-box reinforcement learning with movement primitives","volume-title":"Proc. Conf. Robot Learn.","author":"Otto","year":"2023"},{"key":"ref30","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deisenroth","year":"2011"},{"key":"ref31","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.","volume":"31","author":"Chua","year":"2018"},{"key":"ref32","first-page":"8234","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Buckman","year":"2018"},{"key":"ref33","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Janner","year":"2019"},{"key":"ref34","first-page":"1","article-title":"Data efficient reinforcement learning for legged robots","volume-title":"Proc. Conf. Robot Learn.","author":"Yang","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3284362"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/9781108348973"},{"key":"ref37","first-page":"944","article-title":"Automatic gait optimization with Gaussian process regression","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","volume":"7","author":"Lizotte","year":"2007"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989111"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989186"},{"key":"ref40","first-page":"41","article-title":"Local Bayesian optimization of motor skills","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Akrour","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.3389\/frobt.2022.799893","article-title":"Robot learning from randomized simulations: A review","volume":"9","author":"Muratore","year":"2022","journal-title":"Front. Robot. AI"},{"volume-title":"Gaussian Processes for Machine Learning","year":"2006","author":"Rasmussen","key":"ref43"},{"volume-title":"Introduction to Optimization","year":"1987","author":"Polyak","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1017\/9781108690935"},{"key":"ref46","first-page":"4291","article-title":"Multi-information source optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Poloczek","year":"2017"},{"issue":"4","key":"ref47","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1023\/A:1008306431147","article-title":"Efficient global optimization of expensive black-box functions","volume":"13","author":"Jones","year":"1998","journal-title":"J. Glob. Optim."},{"key":"ref48","first-page":"1805","article-title":"Simple random search of static linear policies is competitive for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Mania","year":"2018"},{"issue":"6","key":"ref49","first-page":"1809","article-title":"Entropy search for information-efficient global optimization","volume":"13","author":"Hennig","year":"2012","journal-title":"J. Mach. Learn. Res."},{"article-title":"Fancy gym","volume-title":"Auton. Learn. Robots Lab (ALR) KIT","author":"Otto","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989607"},{"key":"ref52","first-page":"1040","article-title":"Learning from demonstration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"9","author":"Schaal","year":"1996"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref54","first-page":"73497","article-title":"The behavior and convergence of local Bayesian optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wu","year":"2023"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8860\/10778592\/10874195.pdf?arnumber=10874195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T05:07:38Z","timestamp":1744088858000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10874195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tro.2025.3539192","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"type":"print","value":"1552-3098"},{"type":"electronic","value":"1941-0468"}],"subject":[],"published":{"date-parts":[[2025]]}}}