Reinforcement Learning : Optimal Feedback Control with Industrial Applications / Jinna Li, Frank L. Lewis, Jialu Fan.
Li, Jinna.; Lewis, Frank L.; Fan, Jialu.
2023
Q325.6
Available Online

Linked e-resources

Linked Resource Online Access
Concurrent users Unlimited
Authorized users Authorized users
Document Delivery Supplied Can lend chapters, not whole ebooks

Details

Title Reinforcement Learning : Optimal Feedback Control with Industrial Applications / Jinna Li, Frank L. Lewis, Jialu Fan.
Author Li, Jinna.
ISBN 9783031283949
3031283945
3031283937
9783031283932
DOI https://doi.org/10.1007/978-3-031-28394-9
Imprint Cham : Springer International Publishing AG, 2023.
Language English
Description 1 online resource (xvi, 310 pages) : illustrations (chiefly color).
Other Standard Identifiers 10.1007/978-3-031-28394-9 doi
Call Number Q325.6
Dewey Decimal Classification 006.3/1
Summary This book offers a thorough introduction to the basics and scientific and technological innovations involved in the modern study of reinforcement-learning-based feedback control. The authors address a wide variety of systems including work on nonlinear, networked, multi-agent and multi-player systems. A concise description of classical reinforcement learning (RL), the basics of optimal control with dynamic programming and network control architectures, and a brief introduction to typical algorithms build the foundation for the remainder of the book. Extensive research on data-driven robust control for nonlinear systems with unknown dynamics and multi-player systems follows. Data-driven optimal control of networked single- and multi-player systems leads readers into the development of novel RL algorithms with increased learning efficiency. The book concludes with a treatment of how these RL algorithms can achieve optimal synchronization policies for multi-agent systems with unknown model parameters and how game RL can solve problems of optimal operation in various process industries. Illustrative numerical examples and complex process control applications emphasize the realistic usefulness of the algorithms discussed. The combination of practical algorithms, theoretical analysis and comprehensive examples presented in Reinforcement Learning will interest researchers and practitioners studying or using optimal and adaptive control, machine learning, artificial intelligence, and operations research, whether advancing the theory or applying it in mineral-process, chemical-process, power-supply or other industries.
Bibliography, etc. Note Includes bibliographical references and index.
Access Note Access limited to authorized users.
Source of Description Description based upon print version of record.
Added Author Lewis, Frank L.
Fan, Jialu.
Series Advances in industrial control.
Available in Other Form Reinforcement Learning
Linked Resources Online Access
Record Appears in Online Resources > Ebooks
All Resources
Intro
Series Editor's Foreword
Preface
Acknowledgements
Contents
Abbreviations
1 Background on Reinforcement Learning and Optimal Control
1.1 Fundamentals of Reinforcement Learning and Recall
1.2 Fundamentals of Optimal Control with Dynamic Programming
1.3 Architecture and Performance of Networked Control System
1.4 The State of the Art and Contributions
References
2 Hinfty Control Using Reinforcement Learning
2.1 Hinfty State Feedback Control of Multi-player Systems
2.1.1 Problem Statement
2.1.2 Solving the Multi-player Zero-Sum Game

2.1.3 Off-Policy Game Q-Learning Technique
2.1.4 Simulation Results
2.2 Hinfty Output Feedback Control of Multi-player Systems
2.2.1 Problem Statement
2.2.2 Solving the Multi-player Zero-Sum Game
2.2.3 Off-Policy Game Q-Learning Technique
2.2.4 Simulation Results
2.3 Conclusion
References
3 Robust Tracking Control and Output Regulation
3.1 Optimal Robust Control Problem Statement
3.2 Theoretical Solutions
3.2.1 Solving the Regulator Equations with Known Dynamics
3.2.2 Solving Problem 3.2 with Known Dynamics
3.3 Data-Driven Solutions

3.3.1 Data-Driven OPCG Q-Learning
3.3.2 No Bias Analysis of the Solution for the Proposed Algorithm
3.4 Illustrative Examples
3.5 Conclusion
References
4 Interleaved Robust Reinforcement Learning
4.1 Robust Controller Design and Simplified HJB Equation
4.2 Interleaved RL for Approximating Robust Control
4.2.1 Theoretical Analysis
4.3 Illustrative Examples
4.4 Conclusion
References
5 Optimal Networked Controller and Observer Design
5.1 Off-Policy Q-Learning for Single-Player Networked Control Systems
5.1.1 Problem Formulation

5.1.2 Optimal Observer Design
5.1.3 Optimal Controller Design
5.1.4 Simulation Results
5.2 Off-Policy Q-Learning for Multi-player Networked Control Systems
5.2.1 Problem Formulation
5.2.2 Main Results
5.2.3 Illustrative Example
5.3 Conclusion
References
6 Interleaved Q-Learning
6.1 Optimal Control for Affine Nonlinear Systems
6.1.1 Problem Statement
6.1.2 On-Policy Q-Learning Formulation
6.2 Off-Policy Q-Learning Technique
6.2.1 Off-Policy and Q-Learning
6.2.2 Derivation of Off-Policy Q-Learning Algorithm

6.2.3 No Bias of Off-Policy Q-Learning Algorithm
6.3 Neural Network-Based Off-Policy Interleaved Q-Learning
6.3.1 Model Neural Network
6.3.2 Actor Neural Network
6.3.3 Critic Neural Network
6.3.4 Interleaved Q-Learning
6.3.5 Optimal Control for Linear Systems
6.4 Illustrative Examples
6.5 Conclusion
References
7 Off-Policy Game Reinforcement Learning
7.1 Graphical Game for Optimal Synchronization
7.1.1 Preliminaries
7.1.2 Multi-agent Graphical Games
7.1.3 Off-Policy Reinforcement Learning Algorithm
7.1.4 Simulation Examples

Browse Subjects

Show more subjects...

Statistics

from
to
Export