{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T05:39:59Z","timestamp":1744695599448,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"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":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160387","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"946-952","source":"Crossref","is-referenced-by-count":2,"title":["Enforcing the consensus between Trajectory Optimization and Policy Learning for precise robot control"],"prefix":"10.1109","author":[{"given":"Quentin Le","family":"Lidec","sequence":"first","affiliation":[{"name":"PSL Research University,Inria - Departement d'Informatique de l'Ecole normale supérieure"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wilson","family":"Jallet","sequence":"additional","affiliation":[{"name":"PSL Research University,Inria - Departement d'Informatique de l'Ecole normale supérieure"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[{"name":"PSL Research University,Inria - Departement d'Informatique de l'Ecole normale supérieure"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[{"name":"PSL Research University,Inria - Departement d'Informatique de l'Ecole normale supérieure"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Carpentier","sequence":"additional","affiliation":[{"name":"PSL Research University,Inria - Departement d'Informatique de l'Ecole normale supérieure"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"End-to-end differentiable physics for learning and control","volume":"31","author":"de avila belbute-peres","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.038"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811647"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062323"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/0728030"},{"key":"ref11","article-title":"Simple random search of static linear policies is competitive for reinforcement learning","volume":"31","author":"mania","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/00207176608921369"},{"key":"ref1","first-page":"222","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"2004","journal-title":"ICINCO"},{"key":"ref17","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref16","first-page":"1","article-title":"Guided policy search","author":"levine","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.052"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3149573"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)61205-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref20","article-title":"Sobolev training for neural networks","volume":"30","author":"czarnecki","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"829","article-title":"Learning complex neural network policies with trajectory optimization","author":"levine","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref21","first-page":"7805","article-title":"Pods: Policy optimization via differentiable simulation","author":"mora","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref28","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"0","journal-title":"NIPS 2017 Workshop on Autodiff"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2019.8700380"},{"key":"ref29","article-title":"Stable-baselines 3: Reliable reinforcement learning implementations","author":"raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref9","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196673"},{"key":"ref3","first-page":"4906","article-title":"Synthesis and stabilization of complex behaviors through online trajectory optimization","author":"tassa","year":"0","journal-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref6"},{"journal-title":"Model Predictive Control Theory Computation and Design","year":"2017","author":"rawlings","key":"ref5"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160387.pdf?arnumber=10160387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:30:03Z","timestamp":1690219803000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160387","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}