{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:00:27Z","timestamp":1764784827507,"version":"build-2065373602"},"reference-count":36,"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\/cdc45484.2021.9683350","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"1560-1567","source":"Crossref","is-referenced-by-count":9,"title":["On the Search for Feedback in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ran","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karthikeya S.","family":"Parunandi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aayushman","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raman","family":"Goyal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suman","family":"Chakravorty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"On the search for feedback in reinforcement learning","year":"2020","author":"wang","key":"ref33"},{"journal-title":"High-Dimensional Probability An Introduction with Applications in Data Science Draft","year":"2018","author":"versyhnin","key":"ref32"},{"key":"ref31","first-page":"300","article-title":"A generalized iterative LQG method for locallyoptimal feedback control of constrained nonlinear stochastic systems","author":"todorov","year":"2005","journal-title":"Proceedings of American Control Conference"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530971"},{"article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","year":"2017","author":"yuhuai","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264294"},{"key":"ref34","article-title":"Decoupled data based approach for learning to control nonlinear dynamical systems","author":"wang","year":"2019","journal-title":"IEEE Transactions on Automatic Control AC"},{"key":"ref10","article-title":"Reproducibility of benchmarked deep reinforcement learning tasks for continuous control","author":"islam","year":"2017","journal-title":"Reproducibility in Machine Learning Workshop ICML’17"},{"journal-title":"Differential Dynamic Programming","year":"1970","author":"jacobsen","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974263"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref14","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":"ref15","article-title":"Learning Complex Neural Network Policies with Trajectory Optimization","author":"levine","year":"2014","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3182\/20140824-6-ZA-1003.00874"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/00207170701364913"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref4","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"International Conference on Machine Learning (ICML)"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref27"},{"article-title":"On the convergence of reinforcement learning","year":"2020","author":"chakravorty","key":"ref3"},{"article-title":"Q-prop: Sample-efficient policy gradient with an off-policy critic","year":"2016","author":"gu","key":"ref6"},{"article-title":"Deepmind control suite","year":"2018","author":"tassa","key":"ref29"},{"key":"ref5","first-page":"5026","article-title":"Mujoco: A physics engine for model-based control","author":"emanuel","year":"2012","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"ref8","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"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6425820"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref2"},{"journal-title":"Robust Adaptive Control","year":"2012","author":"ioannou","key":"ref9"},{"journal-title":"Dynamic Programming and Optimal Control Two Volume Set","year":"1995","author":"bertsekas","key":"ref1"},{"key":"ref20","article-title":"Adaptive Optimal Feedback Control with Learned Internal Dynamics Models, in From Motor Learning to Interaction Learning in Robots","volume":"264","author":"mitrovic","year":"2010","journal-title":"Studies in Computational Intelligence"},{"article-title":"keras-rl","year":"2016","author":"plappert","key":"ref22"},{"article-title":"Optimality and Tractability in Stochastic Nonlinear Control","year":"2020","author":"mohamed","key":"ref21"},{"article-title":"Trust region policy optimization","year":"2017","author":"schulman","key":"ref24"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","author":"powell","year":"2007","journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref25"}],"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\/09683350.pdf?arnumber=9683350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T14:00:35Z","timestamp":1674655235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683350\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683350","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}