Global Convergence of Policy Gradient Primal–Dual Methods for Risk-Constrained LQRs
Author:
Affiliation:
1. Department of Automation and BNRist, Tsinghua University, Beijing, China
2. Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA
Funder
National Natural Science Foundation of China
Tsinghua-Foshan Innovation Special Fund
Tsinghua University Initiative Scientific Research Program
ONR MURI
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Electrical and Electronic Engineering,Computer Science Applications,Control and Systems Engineering
Link
http://xplorestaging.ieee.org/ielx7/9/10109211/10005813.pdf?arnumber=10005813
Reference48 articles.
1. Policy Optimization for $\mathcal{H}_2$ Linear Control with $\mathcal{H}_\infty$ Robustness Guarantee: Implicit Regularization and Global Convergence
2. Natural policy gradient primal-dual method for constrained Markov decision processes;ding;Adv Neural Inf Process Syst,2020
3. On the Linear Convergence of Random Search for Discrete-Time LQR
4. An actor-critic algorithm for constrained Markov decision processes
5. Sample complexity of linear quadratic Gaussian (LQG) control for output feedback systems;zheng;Proc Learn Dyn Control,0
Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Asynchronous Block Parallel Policy Optimization for the Linear Quadratic Regulator*;2024 American Control Conference (ACC);2024-07-10
2. Observer-based differential evolution constrained control for safe reference tracking in robots;Neural Networks;2024-07
3. Data-Enabled Policy Optimization for the Linear Quadratic Regulator;2023 62nd IEEE Conference on Decision and Control (CDC);2023-12-13
4. Risk-Constrained Control of Mean-Field Linear Quadratic Systems;2023 62nd IEEE Conference on Decision and Control (CDC);2023-12-13
5. KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Discrete-Time Systems;2023 62nd IEEE Conference on Decision and Control (CDC);2023-12-13
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3