{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T01:10:56Z","timestamp":1768353056437,"version":"3.49.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"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":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10885802","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"3329-3334","source":"Crossref","is-referenced-by-count":1,"title":["Supervised Learning for Stochastic Optimal Control"],"prefix":"10.1109","author":[{"given":"Vince","family":"Kurtz","sequence":"first","affiliation":[{"name":"California Institute of Technology,Department of Civil and Mechanical Engineering"}]},{"given":"Joel W.","family":"Burdick","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Department of Civil and Mechanical Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref4","volume-title":"Chatgpt to fuel 1.3 trillion ai market by 2032, new report says","author":"Rudnitsky","year":"2023"},{"key":"ref5","article-title":"Reinforcement learning and optimal control","volume":"1","author":"Bertsekas","year":"2019","journal-title":"Athena Scientific"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/9781108380690"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adc9244"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref11","article-title":"Implementation matters in deep rl: A case study on ppo and trpo","volume-title":"International conference on learning representations","author":"Engstrom"},{"key":"ref12","article-title":"What matters for on-policy deep actor-critic methods? a large-scale study","volume-title":"International conference on learning representations","author":"Andrychowicz"},{"key":"ref13","article-title":"The 37 implementation details of proximal policy optimization","author":"Huang","year":"2022","journal-title":"The ICLR Blog Track 2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref15","article-title":"Isaac gym: High performance gpu based physics simulation for robot learning","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems, Datasets and Benchmarks Track","author":"Makoviychuk"},{"key":"ref16","article-title":"Brax-a differentiable physics engine for large scale rigid body simulation","author":"Freeman","year":"2021"},{"key":"ref17","volume-title":"Mujoco xla","year":"2024"},{"key":"ref18","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning.","author":"Rudin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/16m1080173"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.95.200201"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0710743106"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/16M105767X"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Lillicrap"},{"key":"ref24","first-page":"7224","article-title":"Value iteration in continuous actions, states and time","volume-title":"International Conference on Machine Learning.","author":"Lutter"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.007"},{"key":"ref26","article-title":"Bridging physics-informed neural networks with reinforcement learning: Hamilton-jacobi-bellman proximal policy optimization (hjbppo)","volume-title":"ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems","author":"Mukherjee"},{"key":"ref27","article-title":"Revisiting continuous-time reinforcement learning. a study of hjb solvers based on pinns and fems","volume-title":"European Workshop on Reinforcement Learning","author":"Shilova"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.851439"},{"key":"ref29","article-title":"Analysis of temporal-diffference learning with function approximation","volume":"9","author":"Tsitsiklis","year":"1996","journal-title":"Advances in neural information processing systems"},{"issue":"5","key":"ref30","article-title":"Finite-time bounds for fitted value iteration","volume":"9","author":"Munos","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","first-page":"640","article-title":"Hjb optimal feedback control with deep differential value functions and action constraints","volume-title":"Conference on Robot Learning.","author":"Lutter"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3206735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31954-2_31"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040310"},{"key":"ref35","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"Theodorou","year":"2010","journal-title":"The Journal of Machine Learning Research"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2210294"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1997.657832"},{"key":"ref39","article-title":"Stop regressing: Training value functions via classification for scalable deep rl","author":"Farebrother","year":"2024","journal-title":"arXiv preprint arXiv:2403.03950"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.562300"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/0470080493"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1214\/14-AOP920"},{"key":"ref43","article-title":"Predictive sampling: Real-time behaviour synthesis with mujoco","author":"Howell","year":"2022","journal-title":"arXiv preprint arXiv:2212.00541"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","location":"Milan, Italy","start":{"date-parts":[[2024,12,16]]},"end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10885802.pdf?arnumber=10885802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T07:33:27Z","timestamp":1740641607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10885802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10885802","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}