How are policy gradient methods affected by the limits of control?
Author:
Affiliation:
1. KTH Royal Institute of Technology,Division of Decision and Control Systems
2. ETH Zurich,Automatic Control Laboratory
3. University of Pennsylvania,Department of Electrical and Systems Engineering
Funder
Google
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9992315/9992317/09992612.pdf?arnumber=9992612
Reference30 articles.
1. Mastering the game of Go without human knowledge
2. Global convergence of policy gradient methods for the linear quadratic regulator;Fazel
3. The gap between model-based and model-free methods on the linear quadratic regulator: An asymptotic viewpoint;Tu
4. Linear Systems can be Hard to Learn
5. On uninformative optimal policies in adaptive lqr with unknown b-matrix;Ziemann,2021
Cited by 5 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. Oracle Complexity Reduction for Model-Free LQR: A Stochastic Variance-Reduced Policy Gradient Approach;2024 American Control Conference (ACC);2024-07-10
2. On the Hardness of Learning to Stabilize Linear Systems;2023 62nd IEEE Conference on Decision and Control (CDC);2023-12-13
3. The Fundamental Limitations of Learning Linear-Quadratic Regulators;2023 62nd IEEE Conference on Decision and Control (CDC);2023-12-13
4. Statistical Learning Theory for Control: A Finite-Sample Perspective;IEEE Control Systems;2023-12
5. Toward a Theoretical Foundation of Policy Optimization for Learning Control Policies;Annual Review of Control, Robotics, and Autonomous Systems;2023-05-03
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