{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:27:30Z","timestamp":1740101250436,"version":"3.37.3"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992367","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"1588-1595","source":"Crossref","is-referenced-by-count":1,"title":["A Homotopic Approach to Policy Gradients for Linear Quadratic Regulators with Nonlinear Controls"],"prefix":"10.1109","author":[{"given":"Craig Xu","family":"Chen","sequence":"first","affiliation":[{"name":"Duke University,Department of Mathematics,United States"}]},{"given":"Andrea","family":"Agazzi","sequence":"additional","affiliation":[{"name":"Duke University,Department of Mathematics,United States"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cdc51059.2022.9992367"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref7","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"2000","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"ref8","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"80","author":"Haarnoja"},{"key":"ref9","first-page":"10170","article-title":"On the global convergence rates of softmax policy gradient methods","volume-title":"Proceedings of Machine Learning and Systems","author":"Mei"},{"article-title":"Qualitatively characterizing neural network optimization problems","volume-title":"International Conference on Learning Representations","author":"Goodfellow","key":"ref10"},{"key":"ref11","article-title":"Global optimality guarantees for policy gradient methods","volume-title":"CoRR","author":"Bhandari","year":"2019"},{"key":"ref12","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"80","author":"Fazel"},{"article-title":"Lqr through the lens of first order methods: Discrete-time case","year":"2019","author":"Bu","key":"ref13"},{"key":"ref14","first-page":"8353","article-title":"Provably global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost","volume-title":"Advances in Neural Information Processing Systems 32.","author":"Yang","year":"2019"},{"key":"ref15","first-page":"10565","article-title":"Neural trust region\/proximal policy optimization attains globally optimal policy","volume-title":"Advances in Neural Information Processing Systems 32.","author":"Liu","year":"2019"},{"key":"ref16","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"37","author":"Schulman"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref18","article-title":"Optimality and approximation with policy gradient methods in markov decision processes","volume-title":"CoRR","author":"Agarwal","year":"2019"},{"key":"ref19","article-title":"Neural policy gradient methods: Global optimality and rates of convergence","volume-title":"International Conference on Learning Representations","author":"Wang","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01920-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3734179"},{"article-title":"How to discount deep reinforcement learning: Towards new dynamic strategies","year":"2016","author":"Fran\u00e7ois-Lavet","key":"ref22"},{"key":"ref23","first-page":"10130","article-title":"Taylor expansion of discount factors","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"139","author":"Tang"},{"key":"ref24","first-page":"29274","article-title":"Stabilizing dynamical systems via policy gradient methods","volume":"34","author":"Perdomo","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Learning stabilizing controllers of linear systems via discount policy gradient","year":"2021","author":"Zhao","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cdc51059.2022.9992367"},{"key":"ref27","first-page":"295","article-title":"Reinforcement learning applied to linear quadratic regulation","volume-title":"Advances in Neural Information Processing Systems 5.","author":"Bradtke","year":"1993"},{"key":"ref28","article-title":"Learning linear dynamical systems via spectral filtering","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Hazan","year":"2017"},{"key":"ref29","article-title":"Spectral filtering for general linear dynamical systems","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Hazan","year":"2018"},{"article-title":"Towards provable control for unknown linear dynamical systems","volume-title":"6th International Conference on Learning Representations, ICLR 2018","author":"Arora","key":"ref30"},{"key":"ref31","first-page":"5005","article-title":"Least-squares temporal difference learning for the linear quadratic regulator","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Tu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-019-09426-y"},{"key":"ref33","article-title":"Learning robust control for LQR systems with multiplicative noise via policy gradient","volume-title":"CoRR","author":"Gravell","year":"2019"},{"volume-title":"Optimal Control: Linear Quadratic Methods.","year":"1990","author":"Anderson","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2616644"},{"issue":"1","key":"ref36","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proceedings of the 31st International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"32","author":"Silver"},{"key":"ref37","article-title":"On the power and limitations of random features for understanding neural networks","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Yehudai","year":"2019"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","start":{"date-parts":[[2022,12,6]]},"location":"Cancun, Mexico","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992367.pdf?arnumber=9992367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T09:27:07Z","timestamp":1709371627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992367","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}