Deep reinforcement learning for wireless sensor scheduling in cyber-physical systems

DOI10.1016/j.automatica.2019.108759zbMath1440.93155arXiv1809.05149OpenAlexW2994803162MaRDI QIDQ2173933

Daniel E. Quevedo, Alex S. Leong, Ling Shi, Holger Karl, Arunselvan Ramaswamy

Publication date: 17 April 2020

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1809.05149

zbMATH Keywords

Markov decision processcyber-physical systemsdeep reinforcement learning algorithmscheduling of sensor transmissions

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Frequency-response methods in control theory (93C80) Markov and semi-Markov decision processes (90C40) Networked control (93B70)

Related Items (9)

On extended state estimation for nonlinear uncertain systems with round-robin protocol ⋮ Model-free design of stochastic LQR controller from a primal-dual optimization perspective ⋮ Rollout approach to sensor scheduling for remote state estimation under integrity attack ⋮ Statistical learning for analysis of networked control systems over unknown channels ⋮ Optimal transmission strategy for multiple Markovian fading channels: existence, structure, and approximation ⋮ Optimal sensor scheduling for remote state estimation with limited bandwidth: a deep reinforcement learning approach ⋮ Multi-channel transmission scheduling with hopping scheme under uncertain channel states ⋮ Transmission scheduling for multi-process multi-sensor remote estimation via approximate dynamic programming ⋮ Model-free optimal control of discrete-time systems with additive and multiplicative noises

Uses Software

• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal LQG control across packet-dropping links
• Stability of Kalman filtering with Markovian packet losses
• Optimal scheduling of multiple sensors over shared channels with packet transmission constraint
• Optimal sensor scheduling for multiple linear dynamical systems
• Redundant data transmission in control/estimation over lossy networks
• On infinite-horizon sensor scheduling
• Learning Algorithms for Markov Decision Processes with Average Cost
• On the Optimal Solutions of the Infinite-Horizon Linear Sensor Scheduling Problem
• Learning in Wireless Control Systems Over Nonstationary Channels
• Kalman Filtering Over a Packet-Dropping Network: A Probabilistic Perspective
• Sensor Scheduling in Variance Based Event Triggered Estimation With Packet Drops

This page was built for publication: Deep reinforcement learning for wireless sensor scheduling in cyber-physical systems