Primal-Dual Q-Learning Framework for LQR Design

Donghwan Lee; Jianghai Hu

首页> 外文期刊>IEEE Transactions on Automatic Control >Primal-Dual Q-Learning Framework for LQR Design

【24h】

Primal-Dual Q-Learning Framework for LQR Design

机译：LQR设计的原始对偶Q学习框架

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Recently, reinforcement learning (RL) is receiving more and more attentions due to its successful demonstrations outperforming human performance in certain challenging tasks. The goal of this paper is to study a new optimization formulation of the linear

机译：近来，强化学习（RL）在某些挑战性任务中的成功演示胜过人类的表现，因此受到越来越多的关注。本文的目的是研究线性优化的新公式

著录项

来源
《IEEE Transactions on Automatic Control》 |2019年第9期|3756-3763|共8页
作者
Donghwan Lee; Jianghai Hu;
展开▼
作者单位

Coordinated Science Laboratory University of Illinois at Urbana-Champaign Champaign IL USA;

Department of Electrical and Computer Engineering Purdue University West Lafayette IN USA;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Optimization; Symmetric matrices; Linear systems; Standards; Trajectory; Reinforcement learning; Regulators;

机译：优化;对称矩阵线性系统;标准;弹道;强化学习;调压器;

相似文献

外文文献
中文文献
专利

1. Quaternion-Based LQR Spacecraft Control Design Is a Robust Pole Assignment Design [J] . Yaguang Yang Journal of aerospace engineering . 2014,第1期

机译：基于四元数的LQR航天器控制设计是一种鲁棒的极点分配设计
2. Problem of precision missile guidance: LQR and H∞ control frameworks [J] . Savkin A.V., Pathirana P.N., Faruqi F.A. IEEE Transactions on Aerospace and Electronic Systems . 2003,第3期

机译：精确导弹制导问题：LQR和H∞控制框架
3. Problem of precision missile guidance: LQR and H/sup /spl infin// control frameworks [J] . Savkin A.V., Pathirana P.N., Faruqi F.A. IEEE Transactions on Aerospace and Electronic Systems . 2003,第3期

机译：精确导弹制导问题：LQR和H / sup / spl infin //控制框架
4. Stochastic Primal-Dual Q-Learning Algorithm For Discounted MDPs [C] . Donghwan Lee, Niao He Annual American Control Conference . 2019

机译：折扣MDP的随机原始对偶Q学习算法
5. A Comparison of the Performance of Neural Q-learning and Soar-RL on a Derivative of the Block Design (BD)/Block Design Multiple Choice (BDMC) Subtests on the WISC-IV Intelligence Test. [D] . Bell, Charreau Sieanna. 2011

机译：在WISC-IV智力测验的区块设计（BD）/区块设计多项选择（BDMC）子测验的衍生物上，神经Q学习和Soar-RL的性能比较。
6. A primal-dual algorithm framework for convex saddle-point optimization [O] . Benxin Zhang, Zhibin Zhu -1

机译：凸鞍点优化的原对偶算法框架
7. Deep Q-Learning Framework for Improving Spectral Efficiency in D2D Communication [O] . Lucas Pires, Paulo Carvalho 2020

机译：深度Q学习框架，用于提高D2D通信中的光谱效率

Primal-Dual Q-Learning Framework for LQR Design

摘要

著录项

相似文献

相关主题

期刊订阅