{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:20:46Z","timestamp":1772205646807,"version":"3.50.1"},"reference-count":53,"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":"am","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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1932187"],"award-info":[{"award-number":["1932187"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2026479"],"award-info":[{"award-number":["2026479"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2222815"],"award-info":[{"award-number":["2222815"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2315396"],"award-info":[{"award-number":["2315396"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100030708","name":"Artificial and Natural Intelligence Toulouse Institute","doi-asserted-by":"publisher","award":["19-P3IA-0004"],"award-info":[{"award-number":["19-P3IA-0004"]}],"id":[{"id":"10.13039\/100030708","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"France 2030"},{"name":"PR[AI]RIE-PSAI AI cluster","award":["ANR-23-IACL-0008"],"award-info":[{"award-number":["ANR-23-IACL-0008"]}]},{"name":"French Government"},{"name":"management of Agence Nationale de la Recherche","award":["ANR-22-CE33-0008"],"award-info":[{"award-number":["ANR-22-CE33-0008"]}]},{"name":"European Union through the AGIMUS","award":["101070165"],"award-info":[{"award-number":["101070165"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/lra.2025.3577875","type":"journal-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:43:39Z","timestamp":1749231819000},"page":"7563-7570","source":"Crossref","is-referenced-by-count":4,"title":["Infinite-Horizon Value Function Approximation for Model Predictive Control"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5552-9898","authenticated-orcid":false,"given":"Armand","family":"Jordana","sequence":"first","affiliation":[{"name":"Machines in Motion Laboratory, New York University, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9025-6143","authenticated-orcid":false,"given":"S\u00e9bastien","family":"Kleff","sequence":"additional","affiliation":[{"name":"Machines in Motion Laboratory, New York University, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6701-1884","authenticated-orcid":false,"given":"Arthur","family":"Haffemayer","sequence":"additional","affiliation":[{"name":"LAAS-CNRS, CNRS, Université de Toulouse, Toulouse, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6599-7302","authenticated-orcid":false,"given":"Joaquim","family":"Ortiz-Haro","sequence":"additional","affiliation":[{"name":"Machines in Motion Laboratory, New York University, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6585-2894","authenticated-orcid":false,"given":"Justin","family":"Carpentier","sequence":"additional","affiliation":[{"name":"Inria - Département d'Informatique de l'École normale supérieure, PSL Research University, Paris, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8090-0601","authenticated-orcid":false,"given":"Nicolas","family":"Mansard","sequence":"additional","affiliation":[{"name":"LAAS-CNRS, CNRS, Université de Toulouse, Toulouse, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6458-9112","authenticated-orcid":false,"given":"Ludovic","family":"Righetti","sequence":"additional","affiliation":[{"name":"Machines in Motion Laboratory, New York University, New York, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353843"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800124"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068908"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.128"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46024-6","volume-title":"Nonlinear Model Predictive Control","author":"Grne","year":"2017"},{"key":"ref7","article-title":"Reinforcement learning and optimal control","volume":"1","author":"Bertsekas","year":"2019","journal-title":"Athena Sci."},{"key":"ref8","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref9","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Proc. Conf. Robot Learn.","author":"Agarwal","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adc9244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160216"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)00073-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00214-9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/9.995049"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00174-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2003.11.014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2594381"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802334"},{"key":"ref25","article-title":"Using local trajectory optimizers to speed up global optimization in dynamic programming","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Atkeson","year":"1993"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614995"},{"key":"ref27","first-page":"1","article-title":"Guided policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Levine","year":"2013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2014.x.052"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.01.022"},{"key":"ref30","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","author":"Lowrey","year":"2018"},{"key":"ref31","first-page":"990","article-title":"Deep value model predictive control","volume-title":"Proc. Conf. Robot Learn.","author":"Hoeller","year":"2020"},{"key":"ref32","first-page":"1105","article-title":"SEAGuL: Sample efficient adversarially guided learning of value functions","volume-title":"Proc. Conf. Learn. Dyn. Control","author":"Landry","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561718"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811993"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3266985"},{"key":"ref36","first-page":"1452","article-title":"Cacto-SL: Using Sobolev learning to improve continuous actor-critic with trajectory optimization","volume-title":"Proc. 6th Annu. Learn. Dyn. Control Conf.","author":"Alboni","year":"2024"},{"key":"ref37","first-page":"931","article-title":"ValueNetQP: Learned one-step optimal control for legged locomotion","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Viereck","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3392154"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2503980"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377184"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561949"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2314612"},{"key":"ref44","volume-title":"Dynamic Programming and Optimal Control: Volume I","author":"Bertsekas","year":"2012"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3166\/ejc.11.310-334"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44184-5_100071"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2024.09.056"},{"issue":"5","key":"ref48","first-page":"815","article-title":"Finite-time bounds for fitted value iteration","volume":"9","author":"Munos","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","article-title":"Stagewise implementations of sequential quadratic programming for model-predictive control","author":"Jordana","year":"2023"},{"key":"ref50","first-page":"4281","article-title":"Sobolev training for neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Czarnecki","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/UR61395.2024.10597485"},{"key":"ref52","article-title":"Drop: Dexterous reorientation via online planning","author":"Li","year":"2024"},{"key":"ref53","article-title":"Full-order sampling-based MPC for torque-level locomotion control via diffusion-style annealing","author":"Xue","year":"2024"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/11008675\/11027777-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11008675\/11027777.pdf?arnumber=11027777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:40:50Z","timestamp":1750268450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11027777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":53,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3577875","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}