Deep Reinforcement Learning for Continuous-time Self-triggered Control <ce:cross-ref refid='fn1'> <ce:sup loc='post'>?</ce:sup> </ce:cross-ref>

Ran Wang; Ibuki Takeuchi; Kenji Kashima

首页> 外文期刊>IFAC PapersOnLine >Deep Reinforcement Learning for Continuous-time Self-triggered Control ?

【24h】

Deep Reinforcement Learning for Continuous-time Self-triggered Control ?

机译：持续时间自触发控制的深度加强学习？

获取原文

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

In recent years, the trade-off between communication cost and control performance has become increasingly important. Among various control architectures, self-triggered controllers decide the next communication (state observation and action determination) timing online in a state-dependent manner. However, it should be emphasized that most of the existing methods do not explicitly evaluate the resulting long-run communication cost. In this paper, we formulate an optimal continuous-time self-triggered control problem that takes the communication cost into an explicit account and proposes a design method based on deep reinforcement learning.

机译：近年来，沟通成本与控制业绩之间的权衡变得越来越重要。在各种控制架构中，自触发的控制器以状态相关方式决定下一个通信（状态观察和动作确定）在线在线。但是，应该强调的是，大多数现有方法都没有明确评估结果的长期通信成本。在本文中，我们制定了最佳的连续时间自动触发控制问题，该控制问题将通信成本置于明确账户中，并提出了一种基于深度增强学习的设计方法。

著录项

来源
《IFAC PapersOnLine》 |2021年第14期|共6页
作者
Ran Wang; Ibuki Takeuchi; Kenji Kashima;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种
中图分类
关键词
Self-triggered controldata-driven control system designmachine learning;

机译：自动触发的Controlyata驱动控制系统DesignMachine学习;

相似文献

外文文献
中文文献
专利

1. Deep learning as optimal control problems ? ? [J] . Martin Benning, Elena Celledoni, Matthias J. Ehrhardt, IFAC PapersOnLine . 2021,第9期

机译：深度学习作为最佳控制问题？？
2. H 2 and H ∞ dynamic output feedback control of continuous-time Markov systems with uncertain rates using LMIs * * Supported by the Brazilian agencies CAPES, CNPq, and FAPESP (Proc. 2014/22881-1) [J] . Cecília F. Morais, Márcio F. Braga, Ricardo C.L.F. Oliveira, IFAC PapersOnLine . 2017,第1期

机译：H 2 和H ∞具有不确定率的连续时间Markov系统的动态输出反馈控制使用LMI * < ce：label> * 由巴西CAPES，CNPq和FAPESP机构支持（Proc。2014 / 22881-1）
3. H 2 and H ∞ dynamic output feedback control of continuous-time Markov systems with uncertain rates using LMIs * * Supported by the Brazilian agencies CAPES, CNPq, and FAPESP (Proc. 2014/22881-1) [J] . Cecília F. Morais, Márcio F. Braga, Ricardo C.L.F. Oliveira, IFAC PapersOnLine . 2017,第1期

机译：H 2 和H ∞具有不确定率的连续时间Markov系统的动态输出反馈控制使用LMI * < ce：label> * 由巴西CAPES，CNPq和FAPESP机构支持（Proc。2014 / 22881-1）
4. Reinforcement Learning Based Continuous-Time On-line Spacecraft Dynamics Control: Case Study of NASA SPHERES Spacecraft [C] . Fei Sun, Kamran Turkoglu AIAA guidance, navigation, and control conference;AIAA SciTech forum . 2018

机译：基于强化学习的连续时间在线航天器动力学控制：NASA SPHERES航天器案例研究
5. Decentralized Deep Reinforcement Learning for Network Level Traffic Signal Control [D] . Guo, Jin . 2020

机译：网络级交通信号控制分散的深度增强学习
6. Deep Reinforcement Learning Controller for 3D Path Following and Collision Avoidance by Autonomous Underwater Vehicles [O] . Simen Theie Havenstrøm, Adil Rasheed, Omer San 2020

机译：3D路径深度加强学习控制器跟踪和自动水下车辆的避免避免
7. SymposiumSubspecialty Certification: Current Status of Orthopaedic Subspecialty Certification* [O] . Keith H. Bridwell 2006

机译：Symposium 亚专业认证：矫形亚专业证书的当前状态 * / cross-ref>

Deep Reinforcement Learning for Continuous-time Self-triggered Control ?

摘要

著录项

相似文献

相关主题

期刊订阅