Published on Thu Sep 13 2018

Deep Reinforcement Learning for Event-Triggered Control

Dominik Baumann, Jia-Jie Zhu, Georg Martius, Sebastian Trimpe

Event-triggered control (ETC) methods can achieve high-performance control. They are often based on a mathematical model of the system. We show how deep reinforcement learning (DRL) algorithms can be leveraged to learn control and communication behavior from scratch.

0
0
0
Abstract

Event-triggered control (ETC) methods can achieve high-performance control with a significantly lower number of samples compared to usual, time-triggered methods. These frameworks are often based on a mathematical model of the system and specific designs of controller and event trigger. In this paper, we show how deep reinforcement learning (DRL) algorithms can be leveraged to simultaneously learn control and communication behavior from scratch, and present a DRL approach that is particularly suitable for ETC. To our knowledge, this is the first work to apply DRL to ETC. We validate the approach on multiple control tasks and compare it to model-based event-triggering frameworks. In particular, we demonstrate that it can, other than many model-based ETC designs, be straightforwardly applied to nonlinear systems.

Sun Sep 27 2020
Machine Learning
Machine Learning in Event-Triggered Control: Recent Advances and Open Issues
Network Control Systems (NCSs) face the challenges of limited communication bandwidth resources, reliability and lack of knowledge of network dynamics. Machine learning (ML) combined with event-triggered control (ETC) has the potential to ease some of these challenges.
0
0
0
Sun Oct 25 2020
Machine Learning
How to Make Deep RL Work in Practice
In recent years, challenging control problems have become solvable with deep reinforcement learning (RL) To be able to use RL for large-scale real-world applications, a certain degree of reliability is necessary. Reported results of state-of-the-art algorithms are often difficult to reproduce.
0
0
0
Wed May 15 2019
Machine Learning
Deep reinforcement learning for scheduling in large-scale networked control systems
DIRA is tailored towards large-scale problems where control and scheduling need to act jointly. DIRA can be used to schedule general time-domain optimization based controllers.
0
0
0
Tue Jan 02 2018
Artificial Intelligence
DeepMind Control Suite
The DeepMind Control Suite is a set of continuous control tasks. It is intended to serve as performance benchmarks for reinforcement learning agents. The tasks are written in Python and powered by the MuJoCo physics engine.
0
0
0
Tue Aug 11 2020
Machine Learning
Learning Event-triggered Control from Data through Joint Optimization
Event-triggered methods aim to achieve high control performance while only closing the feedback loop when needed. This enables resource savings, e.g., network bandwidth if control commands are sent via communication networks. The method's applicability to real-world scenarios is demonstrated through experiments.
0
0
0
Sun Nov 15 2020
Machine Learning
Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking
Tonic is a Python library for deep reinforcement learning research. It allows researchers to quickly implement new ideas and measure their importance. Tonic has several baseline agents and support for TensorFlow and PyTorch.
0
0
0