A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Design and application of adaptive PID controller based on asynchronous advantage actor–critic learning method
2019
Wireless networks
To address the problems of the slow convergence and inefficiency in the existing adaptive PID controllers, we propose a new adaptive PID controller using the asynchronous advantage actor-critic (A3C) algorithm ...
Firstly, the controller can train the multiple agents of the actor-critic structures in parallel exploiting the multi-thread asynchronous learning characteristics of the A3C structure. ...
Google's DeepMind team proposed the asynchronous advantage actor-critic (A3C) learning algorithm [14, 15] . ...
doi:10.1007/s11276-019-02225-x
fatcat:jqlgojvabrd7famurtm5ggwhea
Editorial: Advance of simulations and techniques for communication networks and information systems
2021
Wireless networks
Nowadays, following the successful application of wireless communication and the fast development of the fifth generation communication (5G), a large number of new emerging applications and services, such ...
How to simulate the behavior of services and verify the functions of applications in the network? ...
1 School of Information and Communication Engineering, Acknowledgements The guest editors are thankful to our reviewers for their effort in reviewing the manuscripts. ...
doi:10.1007/s11276-021-02601-6
fatcat:6zvqqznkpregnf7feeern63fhu
Online Reinforcement Learning-Based Control of an Active Suspension System Using the Actor Critic Approach
2020
Applied Sciences
The actor produces the actions, and the critic criticizes the actions taken based on the new state of the system. ...
In this paper, a controller learns to adaptively control an active suspension system using reinforcement learning without prior knowledge of the environment. ...
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/app10228060
fatcat:t3a2sa527ffonophc2u3y5f5ye
Research on Obstacle Avoidance Planning for UUV Based on A3C Algorithm
2023
Journal of Marine Science and Engineering
As a type of deep reinforcement learning algorithm, the A3C (Asynchronous Advantage Actor-Critic) algorithm can effectively utilize computer resources and improve training efficiency by synchronously training ...
Actor-Critic in multiple threads. ...
Conflicts of Interest: The authors declare no conflicts of interest. ...
doi:10.3390/jmse12010063
fatcat:3lha3tclbveqjdjzmlmajwzaxe
Deep Deterministic Policy Gradient to Regulate Feedback Control Systems Using Reinforcement Learning
2022
Computers Materials & Continua
We propose an adaptive speed control of the motor system based on depth deterministic strategy gradient (DDPG). The actor-critic scenario using DDPG is implemented to build the RL agent. ...
The performance of the proposed RL algorithm is compared with a proportional integral derivative (PID) controller and a linear quadratic regulator (LQR) controller. ...
In further, [14] proposed a deep RL algorithm based on near-end Actor-Critic for feedback control applications. ...
doi:10.32604/cmc.2022.021917
fatcat:db33p2eadrgxpdq52db6l6eh5e
Research on PID Parameter Tuning and Optimization Based on SAC-Auto for USV Path Following
2022
Journal of Marine Science and Engineering
In this paper, a PID parameter tuning and optimizing method based on deep reinforcement learning were proposed to control the USV heading. ...
Secondly, the guidance law on the line-of-sight (LOS) method and the USV heading control system of the PID controller are designed. ...
Institutional Review
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/jmse10121847
fatcat:grkhapqk3fa6ldmfbypsuxeyom
A Survey on Reinforcement Learning in Aviation Applications
[article]
2022
arXiv
pre-print
Compared with model-based control and optimization methods, reinforcement learning (RL) provides a data-driven, learning-based framework to formulate and solve sequential decision-making problems. ...
Then we survey the landscape of existing RL-based applications in aviation. Finally, we summarize the paper, identify the technical gaps, and suggest future directions of RL research in aviation. ...
Asynchronous advantage actor-critic (A3C) [25] uses advantage estimates rather than discounted returns in the actor-critic framework and asynchronously updates both the policy and value networks on multiple ...
arXiv:2211.02147v2
fatcat:y4tqirja3nffpdpmjhka22ibee
Autotuning PID control using Actor-Critic Deep Reinforcement Learning
[article]
2022
arXiv
pre-print
To study this, an algorithm called Advantage Actor Critic (A2C) is implemented on a simulated robot arm. The simulation primarily relies on the ROS framework. ...
In addition, it is studied if the model is able to predict PID parameters based on where an apple is located. ...
I also want to mention the support we have received over the ROS and HEBI forums, which has been a great help over the course of the project and nally, I would like to thank my colleague Leon Eshuijs, ...
arXiv:2212.00013v1
fatcat:lec5qlaykbhufac2b5ntk3jhkq
Intelligent Controller Based on Distributed Deep Reinforcement Learning for PEMFC Air Supply System
2021
IEEE Access
In this paper an intelligent controller based on distributed deep reinforcement learning which exerts better control over the air flux of a proton exchange membrane fuel cell (PEMFC) air supply system ...
Research on the control strategy of air supply system is of great importance and significance in engineering. ...
the control system of PEMFC [16] , a neural PID controller [17] , the fuzzy PID control [18] , a controller based on fuzzy controls combined with PID [19] , the application of feedback linearization ...
doi:10.1109/access.2021.3049162
fatcat:rzys2tzozzg6rp55t4ndhmeh3i
Data-Driven Control Algorithm for Snake Manipulator
2021
Applied Sciences
A data-driven controller based on the deep deterministic policy gradient was trained in order to solve the manipulator system control problem when the control system environment model is uncertain or even ...
After collecting data, the algorithm uses the strong learning and decision-making ability of the deep deterministic strategy gradient to learn these system data. ...
Hybrid algorithm
actor-critic
Asynchronous
advantage
actor-critic (A3C)
Asynchronous training framework,
network structure optimization, and
evaluation point optimization. ...
doi:10.3390/app11178146
fatcat:cxrby7fyqbfklm6nbpfqjn25sy
Deep Reinforcement Learning for Integrated Non-Linear Control of Autonomous UAVs
2022
Processes
Results indicate the significance of the proposed control architecture and its inherent capability to adapt dynamically to the changing environment, thereby making it of significant utility to airborne ...
Conventional DDPG algorithm after being modified in its learning architecture becomes capable of intelligently handling the continuous state and control space domains besides controlling the platform in ...
Informed Consent Statement: Not applicable. Data Availability Statement: Not applicable.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/pr10071307
fatcat:k5brr2gafrdihmbxvisrsvf5om
Drone Deep Reinforcement Learning: A Review
2021
Electronics
In this paper, we described the state of the art of one subset of these algorithms: the deep reinforcement learning (DRL) techniques. ...
We noted that most of these DRL methods were designed to ensure stable and smooth UAV navigation by training computer-simulated environments. ...
Special acknowledgement to Robotics and Internet-of-Things Lab (RIOTU), Prince Sultan University, Riyadh, Saudi Arabia.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/electronics10090999
doaj:57ededb7d1a0445eaf34975cb6625c1f
fatcat:kya3fbblszd27i4exlybnji4ni
One-Layer Real-Time Optimization Using Reinforcement Learning: A Review with Guidelines
2023
Processes
The typical control and optimization system hierarchy depend on the layers of real-time optimization, supervisory control, and regulatory control. ...
The literature about each mentioned layer is reviewed, supporting the proposal of a benchmark study of reinforcement learning using a one-layer approach. ...
For regulatory control, RL can be understood as an adaptive controller, which is similar to the proportional-integral-derivative (PID) controller (for more details on PID control methods, see Kumar et ...
doi:10.3390/pr11010123
fatcat:tlthimzdzrhyzmkyrgopbzmmki
Adaptive Nonlinear Model Predictive Horizon Using Deep Reinforcement Learning for Optimal Trajectory Planning
2022
Drones
The results demonstrate the learning curves, sample complexity, and stability of the DRL-based adaptation scheme and show the superior performance of adaptive NMPH relative to our earlier designs. ...
This is done by tuning the NMPH's parameters online using two different actor-critic DRL-based algorithms, deep deterministic policy gradient (DDPG) and soft actor-critic (SAC). ...
(TD3) [21] , soft actor-critic (SAC) [22] , and asynchronous advantage actor-critic (A3C) [23] ) algorithms. ...
doi:10.3390/drones6110323
fatcat:olu36goyzvganhre7kjkbiogzm
Recent Advances in Reinforcement Learning Applications for Building Energy Management: A Mini Review
2022
Proceedings of International Exchange and Innovation Conference on Engineering & Sciences (IEICES)
Furthermore, the combination of RL with other deep learning methods is discussed. ...
As a state-of-the-art technology in smart grid building applications, RL is applied for control purposes and forecasting enhancement. ...
Compared the prediction performance of three of the most Asynchronous Advantage The ground source heat common DRL algorithms with three conventional machine [38] 2020 Office Building Actor-Critic (A3C, ...
doi:10.5109/5909098
fatcat:i2o7bjvddbfarijnolac635m7u
« Previous
Showing results 1 — 15 out of 367 results