{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T09:53:12Z","timestamp":1787478792793,"version":"build-2736575974"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Italian MUR"},{"name":"PRIN Project DOCEAT","award":["CUP E63C22000410001"],"award-info":[{"award-number":["CUP E63C22000410001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/lra.2023.3266985","type":"journal-article","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T13:52:47Z","timestamp":1681393967000},"page":"3318-3325","source":"Crossref","is-referenced-by-count":23,"title":["CACTO: Continuous Actor-Critic With Trajectory Optimization\u2014Towards Global Optimality"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-2751","authenticated-orcid":false,"given":"Gianluigi","family":"Grandesso","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5672-453X","authenticated-orcid":false,"given":"Elisa","family":"Alboni","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1075-9603","authenticated-orcid":false,"given":"Gastone P. Rosati","family":"Papini","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9041-5175","authenticated-orcid":false,"given":"Patrick M.","family":"Wensing","sequence":"additional","affiliation":[{"name":"Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1275-2851","authenticated-orcid":false,"given":"Andrea Del","family":"Prete","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800124"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029990"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958483"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463154"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4755-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/9.412624"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/9.661081"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2021.3087317"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759553"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref12","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref13","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10070870"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2939174"},{"key":"ref16","first-page":"III-1","article-title":"Guided policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Levine","year":"2013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.052"},{"key":"ref18","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017"},{"key":"ref19","first-page":"3305","article-title":"PsiPhi-Learning: Reinforcement learning with demonstrations using successor features and inverse temporal difference learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Filos","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2653850"},{"key":"ref21","first-page":"2829","article-title":"Continuous deep Q-Learning with model-based acceleration","volume-title":"Proc. 33th Int. Conf. Mach. Learn.","author":"Gu","year":"2016"},{"key":"ref22","first-page":"2052","article-title":"Off-Policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref23","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-68928-5","volume-title":"PyomoOptimization Modeling in Python","author":"Bynum","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-004-0559-y"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.OA-2020-0165"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/060649513"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2307\/2372560"},{"key":"ref31","article-title":"Reproducibility of benchmarked deep reinforcement learning tasks for continuous control","author":"Islam","year":"2017"},{"key":"ref32","first-page":"4278","article-title":"Sobolev training for neural networks","volume-title":"Proc. 17th NeurIPS","author":"Czarnecki","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196673"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560731"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3072783"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10102643\/10101856.pdf?arnumber=10101856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:03:40Z","timestamp":1769493820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10101856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":35,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3266985","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}