{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:04:18Z","timestamp":1729631058055,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"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":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9682829","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"2969-2975","source":"Crossref","is-referenced-by-count":0,"title":["On the Convergence of Reinforcement Learning in Nonlinear Continuous State Space Problems"],"prefix":"10.1109","author":[{"given":"Raman","family":"Goyal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suman","family":"Chakravorty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed Naveed","family":"Gul Mohamed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"On the sample complexity of reinforcement learning","author":"kakade","year":"2003","journal-title":"Ph D dissertation UCL (University College London)"},{"key":"ref11","article-title":"Finite-time bounds for fitted value´ iteration","volume":"9","author":"munos","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","first-page":"1","article-title":"On the sample complexity of the linear quadratic regulator","author":"dean","year":"2019","journal-title":"Foundations of Computational Mathematics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"article-title":"On the optimal feedback law in stochastic optimal nonlinear control","year":"2020","author":"mohamed","key":"ref15"},{"article-title":"On the convergence of reinforcement learning in nonlinear continuous state space problems","year":"2020","author":"goyal","key":"ref16"},{"key":"ref17","volume":"336","author":"courant","year":"1953","journal-title":"Methods of Mathematical Physics Vol II"},{"key":"ref4","article-title":"Model free trajectory optimization for reinforcement learning","author":"akrour","year":"2016","journal-title":"Proc of the ICML"},{"key":"ref3","first-page":"1107","article-title":"Least squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530971"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927530"},{"key":"ref8","article-title":"Learning complex neural network policies with trajectory optimization","author":"levine","year":"2014","journal-title":"Proc of the ICML"},{"key":"ref7","article-title":"Learning neural network policies with guided search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in NIPS"},{"journal-title":"Dynamic Programming","year":"1957","author":"bellman","key":"ref2"},{"journal-title":"Dynamic Programming and Optimal Control Vols I and II","year":"2012","author":"bertsekas","key":"ref1"},{"article-title":"On the sample complexity of reinforcement learning with a generative model","year":"2012","author":"azar","key":"ref9"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2021,12,14]]},"location":"Austin, TX, USA","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09682829.pdf?arnumber=9682829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T14:00:44Z","timestamp":1674655244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9682829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9682829","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}