Reinforcement learning for cyber-physical systems with cybersecurity case studies

✍ Scribed by Li, Chong; Qiu, Meikang

• Publisher: CRC Press
• Year: 2019
• Tongue: English
• Leaves: 257
• Category: Library

✦ Synopsis

Reinforcement Learning for Cyber-Physical Systems: with Cybersecurity Case Studies was inspired by recent developments in the fields of reinforcement learning (RL) and cyber-physical systems (CPSs). Rooted in behavioral psychology, RL is one of the primary strands of machine learning. Different from other machine learning algorithms, such as supervised learning and unsupervised learning, the key feature of RL is its unique learning paradigm, i.e., trial-and-error. Combined with the deep neural networks, deep RL become so powerful that many complicated systems can be automatically managed by AI agents at a superhuman level. On the other hand, CPSs are envisioned to revolutionize our society in the near future. Such examples include the emerging smart buildings, intelligent transportation, and electric grids. However, the conventional hand-programming controller in CPSs could neither handle the increasing complexity of the system, nor automatically adapt itself to new situations that it has never encountered before. The problem of how to apply the existing deep RL algorithms, or develop new RL algorithms to enable the real-time adaptive CPSs, remains open. This book aims to establish a linkage between the two domains by systematically introducing RL foundations and algorithms, each supported by one or a few state-of-the-art CPS examples to help readers understand the intuition and usefulness of RL techniques. Features Introduces reinforcement learning, including advanced topics in RL Applies reinforcement learning to cyber-physical systems and cybersecurity Contains state-of-the-art examples and exercises in each chapter Provides two cybersecurity case studies Reinforcement Learning for Cyber-Physical Systems with Cybersecurity Case Studies is an ideal text for graduate students or junior/senior undergraduates in the fields of science, engineering, computer science, or applied mathematics. It would also prove useful to researchers and engineers interested in cybersecurity, RL, and CPS. The only background knowledge required to appreciate the book is a basic knowledge of calculus and probability theory.  Read more...

Abstract: Reinforcement Learning for Cyber-Physical Systems: with Cybersecurity Case Studies was inspired by recent developments in the fields of reinforcement learning (RL) and cyber-physical systems (CPSs). Rooted in behavioral psychology, RL is one of the primary strands of machine learning. Different from other machine learning algorithms, such as supervised learning and unsupervised learning, the key feature of RL is its unique learning paradigm, i.e., trial-and-error. Combined with the deep neural networks, deep RL become so powerful that many complicated systems can be automatically managed by AI agents at a superhuman level. On the other hand, CPSs are envisioned to revolutionize our society in the near future. Such examples include the emerging smart buildings, intelligent transportation, and electric grids. However, the conventional hand-programming controller in CPSs could neither handle the increasing complexity of the system, nor automatically adapt itself to new situations that it has never encountered before. The problem of how to apply the existing deep RL algorithms, or develop new RL algorithms to enable the real-time adaptive CPSs, remains open. This book aims to establish a linkage between the two domains by systematically introducing RL foundations and algorithms, each supported by one or a few state-of-the-art CPS examples to help readers understand the intuition and usefulness of RL techniques. Features Introduces reinforcement learning, including advanced topics in RL Applies reinforcement learning to cyber-physical systems and cybersecurity Contains state-of-the-art examples and exercises in each chapter Provides two cybersecurity case studies Reinforcement Learning for Cyber-Physical Systems with Cybersecurity Case Studies is an ideal text for graduate students or junior/senior undergraduates in the fields of science, engineering, computer science, or applied mathematics. It would also prove useful to researchers and engineers interested in cybersecurity, RL, and CPS. The only background knowledge required to appreciate the book is a basic knowledge of calculus and probability theory

✦ Table of Contents

Content: Cover
Half Title
Title Page
Copyright Page
Dedication
Contents
Preface
Author Bios
Section I: Introduction
Chapter 1 Overview of Reinforcement Learning
1.1 OVERVIEW OF REINFORCEMENT LEARNING
1.1.1 Introduction
1.1.2 Comparison with Other Machine Learning Methods
1.1.3 An Example of Reinforcement Learning
1.1.4 Applications of Reinforcement Learning
1.2 HISTORY OF REINFORCEMENT LEARNING
1.2.1 Traditional Reinforcement Learning
1.2.2 Deep Reinforcement Learning
1.3 SIMULATION TOOLKITS FOR REINFORCEMENT LEARNING
1.4 REMARKS Chapter 2 Overview of Cyber-Physical Systems and Cybersecurity2.1 INTRODUCTION
2.2 EXAMPLES OF CYBER-PHYSICALSYSTEMS RESEARCH
2.2.1 Resource Allocation
2.2.2 Data Transmission and Management
2.2.3 Energy Control
2.2.4 Model-Based Software Design
2.3 CYBERSECURITY THREATS
2.3.1 Adversaries in Cybersecurity
2.3.2 Objectives of Cybersecurity
2.3.2.1 Confidentiality
2.3.2.2 Integrity
2.3.2.3 Availability
2.3.2.4 Authenticity
2.4 REMARKS
2.5 EXERCISES
Section II: Reinforcement Learning for Cyber-Physical Systems
Chapter 3 Reinforcement Learning Problems 5.4.2 Double Q-Learning5.5 REMARKS
5.6 EXERCISES
Chapter 6 Deep Reinforcement Learning
6.1 INTRODUCTION TO DEEP RL
6.2 DEEP NEURAL NETWORKS
6.2.1 Convolutional Neural Networks
6.2.2 Recurrent Neural Networks
6.3 DEEP LEARNING TO VALUE FUNCTIONS
6.3.1 DQN
6.3.1.1 Example
6.4 DEEP LEARNING TO POLICY FUNCTIONS
6.4.1 DDPG
6.4.2 A3C
6.4.2.1 Example
6.5 DEEP LEARNING TO RL MODEL
6.6 DRL COMPUTATION EFFICIENCY
6.7 REMARKS
6.8 EXERCISES
Section III: Case Studies
Chapter 7 Reinforcement Learning for Cybersecurity
7.1 TRADITIONAL CYBERSECURITY METHODS

✦ Subjects

Reinforcement learning.;Cooperating objects (Computer systems);Computer security.;COMPUTERS -- General.;COMPUTERS -- Machine Theory.;COMPUTERS -- Security -- General.;COMPUTERS -- Computer Engineering.