{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:46:48Z","timestamp":1765547208097,"version":"build-2065373602"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"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":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383842","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"795-800","source":"Crossref","is-referenced-by-count":4,"title":["Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding"],"prefix":"10.1109","author":[{"given":"Tongzheng","family":"Ren","sequence":"first","affiliation":[{"name":"Google Brain and University of Texas,Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaolin","family":"Ren","sequence":"additional","affiliation":[{"name":"Harvard University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Li","sequence":"additional","affiliation":[{"name":"Harvard University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Dai","sequence":"additional","affiliation":[{"name":"Google Brain and Georgia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1686","article-title":"A free lunch from the noise: Provable and practical exploration for representation learning","volume-title":"Uncertainty in Artificial Intelligence","author":"Ren","year":"2022"},{"issue":"1","key":"ref2","volume-title":"Applied nonlinear control","volume":"199","author":"Slotine","year":"1991"},{"volume-title":"Nonlinear Control","year":"2015","author":"Khalil","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(94)00113-W"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/s0005-1098(00)00058-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(89)90031-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1470308"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1201\/9781498701822"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.06.010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/37.165507"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1111\/j.1934-6093.1999.tb00002.x"},{"key":"ref12","volume-title":"Model predictive control: theory, computation, and design","volume":"2","author":"Rawlings","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/10997703_14"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.17.5.315"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.03.046"},{"key":"ref16","first-page":"15312","article-title":"Information theoretic regret bounds for online nonlinear control","volume":"33","author":"Kakade","year":"2020","journal-title":"Adv. in Neural Info. Processing Systems"},{"key":"ref17","article-title":"Modelling transition dynamics in mdps with rkhs embeddings","author":"Grunewalder","year":"2012","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"An occupation kernel approach to optimal control","author":"Kamalapurkar","year":"2021","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning","volume":"21","author":"Rahimi","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1561\/2200000036"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1950-0051437-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1953-0052691-0"},{"key":"ref24","article-title":"Random features for large-scale kernel machines","volume":"20","author":"Rahimi","year":"2007","journal-title":"Adv. in Neural Info. Processing Systems"},{"key":"ref25","first-page":"3041","article-title":"Scalable kernel methods via doubly stochastic gradients","volume":"27","author":"Dai","year":"2014","journal-title":"Adv. in Neural Info. Processing Systems"},{"key":"ref26","article-title":"Stochastic nonlinear control via finite-dimensional spectral dynamic embedding","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref28","first-page":"10746","article-title":"Reinforcement learning in feature space: Matrix bandit, kernels, and regret bound","volume-title":"International Conference on Machine Learning","author":"Yang","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2014.7010633"},{"issue":"2","key":"ref30","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1023\/A:1017984413808","article-title":"Near-optimal reinforcement learning in polynomial time","volume":"49","author":"Kearns","year":"2002","journal-title":"Machine learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89722-4_20"},{"issue":"98","key":"ref32","first-page":"1","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"J Mach Learn Res"},{"key":"ref33","article-title":"Politex: Regret bounds for policy iteration using expert prediction","volume-title":"International Conference on Machine Learning","author":"Abbasi-Yadkori","year":"2019"},{"key":"ref34","article-title":"Iterative linear quadratic optimization for nonlinear control: Differentiable programming algorithmic templates","author":"Roulet","year":"2022","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184036"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383842.pdf?arnumber=10383842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:57:46Z","timestamp":1706029066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383842","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}