{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:38:17Z","timestamp":1774021097128,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/lra.2025.3566599","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T17:17:59Z","timestamp":1746206279000},"page":"6880-6887","source":"Crossref","is-referenced-by-count":2,"title":["Towards Safe and Efficient Learning in the Wild: Guiding RL With Constrained Uncertainty-Aware Movement Primitives"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3917-4767","authenticated-orcid":false,"given":"Abhishek","family":"Padalkar","sequence":"first","affiliation":[{"name":"German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC), Weßling, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9555-9517","authenticated-orcid":false,"given":"Freek","family":"Stulp","sequence":"additional","affiliation":[{"name":"German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC), Weßling, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5483-4225","authenticated-orcid":false,"given":"Gerhard","family":"Neumann","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1428-8933","authenticated-orcid":false,"given":"Jo\u00e3o","family":"Silv\u00e9rio","sequence":"additional","affiliation":[{"name":"German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC), Weßling, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/4-431-31381-8_23"},{"key":"ref3","first-page":"2616","article-title":"Probabilistic movement primitives","volume-title":"Proc. 27th Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Paraschos","year":"2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919846363"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965869"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340700"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3126658"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-024-10164-6"},{"key":"ref9","first-page":"729","article-title":"Guided reinforcement learning with learned skills","volume-title":"Proc. Conf. Robot Learn.","author":"Pertsch","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref11","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. 30th Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3207664"},{"key":"ref13","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref15","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref18","article-title":"Residual reinforcement learning from demonstrations","author":"Alakuijala","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150024"},{"key":"ref20","first-page":"531","article-title":"Guided reinforcement learning for robust multi-contact loco-manipulation","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Sleiman","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"ref23","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018"},{"key":"ref24","first-page":"997","article-title":"Safe exploration for optimization with gaussian processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sui","year":"2015"},{"key":"ref25","first-page":"4312","article-title":"Safe exploration in finite Markov decision processes with gaussian processes","volume-title":"Proc. 30th Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Turchetta","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref27","article-title":"Diffusion models for reinforcement learning: A survey","author":"Zhu","year":"2023"},{"key":"ref28","article-title":"Safe offline reinforcement learning with feasibility-guided diffusion model","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zheng","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161065"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196821"},{"key":"ref31","first-page":"5556","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","volume-title":"Int. Conf. Mach. Learn.","author":"Kuznetsov","year":"2020"},{"issue":"268","key":"ref32","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11008675\/10982105.pdf?arnumber=10982105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T05:22:50Z","timestamp":1748582570000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10982105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":32,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3566599","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}