首页> 外文会议>Annual American Control Conference >Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems

【24h】

Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems

机译：马氏跳跃线性系统策略优化方法的收敛性保证

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Recently, policy optimization for control purposes has received renewed attention due to the increasing interest in reinforcement learning. In this paper, we investigate the convergence of policy optimization for quadratic control of Markovian jump linear

机译：最近，由于对强化学习的兴趣日益浓厚，用于控制目的的策略优化受到了越来越多的关注。在本文中，我们研究了马尔可夫跳跃线性二次控制的策略优化收敛性。

著录项

来源
《Annual American Control Conference》|2020年|2882-2887|共6页
会议地点
作者
Joao Paulo Jansch-Porto; Bin Hu; Geir E. Dullerud;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Linear systems; Gradient methods; Convergence; State feedback; Markov processes;

机译：线性系统梯度方法收敛状态反馈马氏过程;

相似文献

外文文献
中文文献
专利

1. Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems [J] . Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Journal of machine learning research . 2020,第a期

机译：无衍生物的政策优化方法：线性二次系统的保证
2. Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems [J] . Dhruv Malik, Ashwin Pananjady, Kush Bhatia, JMLR: Workshop and Conference Proceedings . 2018,第2010期

机译：无衍生物的政策优化方法：线性二次系统的保证
3. Multiple delay-dependent H_∞ guaranteed cost control for uncertain semi-Markovian jump random nonlinear systems with intermittent actuator and sensor faults and input constraint [J] . Sun Shaoxin, Zhang Huaguang, Wang Junyi, International journal of systems science . 2021,第1a4期

机译：具有间歇执行器和传感器故障和输入约束的不确定半市场跳跃随机非线性系统的多次延迟依赖性H_∞保证成本控制
4. Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems [C] . Joao Paulo Jansch-Porto, Bin Hu, Geir E. Dullerud American Control Conference . 2019

机译：Markovian跳跃线性系统政策优化方法的收敛保证
5. Control of time-delayed Markovian jump linear systems. [D] . Beane, Carlos D. 2010

机译：时滞马尔可夫跳跃线性系统的控制。
6. Convergence Analysis and Numerical Study of a Fixed-Point Iterative Method for Solving Systems of Nonlinear Equations [O] . Na Huang, Changfeng Ma -1

机译：求解非线性方程组的不动点迭代法的收敛性分析和数值研究
7. Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems [O] . Joao Paulo Jansch-Porto, Bin Hu, Geir E. Dullerud 2020

机译：Markovian跳跃线性系统政策优化方法的收敛保证
8. Discrete-Time Markovian Jump Linear Systems [R] . Szajowski, K., de Koning, W. L. 1992

机译：离散时间马尔可夫跳跃线性系统

Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems

摘要

著录项

相似文献

相关主题

期刊订阅