A Case Study on the Convergence of Direct Policy Search for Linear Quadratic Gaussian Control-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

A Case Study on the Convergence of Direct Policy Search for Linear Quadratic Gaussian Control

Published:2024-07-10 Issue: Volume:32 Page:3710-3715
ISSN:
Container-title:2024 American Control Conference (ACC)
language:
Short-container-title:

Author:

Keivan Darioush¹,Seiler Peter²,Dullerud Geir¹,Bin H.³

Affiliation:

1. Coordinated Science Laboratory (CSL), University of Illinois at Urbana-Champaign,Department of Mechanical Science & Engineering

2. University of Michigan,Department of Electrical Engineering and Computer Science

3. Coordinated Science Laboratory (CSL), University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering

Funder

NSF

U.S. Office of Naval Research

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx8/10644130/10644150/10644427.pdf?arnumber=10644427

Reference40 articles.

1. Trust region policy optimization;Schulman

2. Proximal policy optimization algorithms;Schulman;arXiv preprint,2017

3. Toward a Theoretical Foundation of Policy Optimization for Learning Control Policies

4. Global convergence of policy gradient methods for the linear quadratic regulator;Fazel

5. LQR through the lens of first order methods: Discrete-time case;Bu;arXiv preprint,2019

同舟云学术

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