Vor Ort
Merkzettel Warenkorb
  • Produktbild: Deep Reinforcement Learning for Wireless Communications and Networking
  • Produktbild: Deep Reinforcement Learning for Wireless Communications and Networking

Deep Reinforcement Learning for Wireless Communications and Networking Theory, Applications and Implementation

152,99 €

inkl. gesetzl. MwSt., Versandkostenfrei

Beschreibung

Produktdetails

Einband

Gebundene Ausgabe

Erscheinungsdatum

25.07.2023

Verlag

John Wiley & Sons Inc

Seitenzahl

288

Maße (L/B/H)

23,5/15,7/2 cm

Gewicht

573 g

Auflage

1. Auflage

Sprache

Englisch

ISBN

978-1-119-87367-9

Beschreibung

Produktdetails

Einband

Gebundene Ausgabe

Erscheinungsdatum

25.07.2023

Verlag

John Wiley & Sons Inc

Seitenzahl

288

Maße (L/B/H)

23,5/15,7/2 cm

Gewicht

573 g

Auflage

1. Auflage

Sprache

Englisch

ISBN

978-1-119-87367-9

Herstelleradresse

Libri GmbH
Europaallee 1
36244 Bad Hersfeld
DE

Email: GPSR Kontakt

Noch keine Bewertungen vorhanden

Verfassen Sie die erste Bewertung zu diesem Artikel

Helfen Sie anderen Kundinnen und Kunden durch Ihre Meinung.

Kundinnen und Kunden meinen

Bewertungen (0)
Die Leseprobe wird geladen.
  • Produktbild: Deep Reinforcement Learning for Wireless Communications and Networking
  • Produktbild: Deep Reinforcement Learning for Wireless Communications and Networking
  • Notes on Contributors xiii
     
    Foreword xiv
     
    Preface xv
     
    Acknowledgments xviii
     
    Acronyms xix
     
    Introduction xxii
     
    Part I Fundamentals of Deep Reinforcement Learning 1
     
    1 Deep Reinforcement Learning and Its Applications 3
     
    1.1 Wireless Networks and Emerging Challenges 3
     
    1.2 Machine Learning Techniques and Development of DRL 4
     
    1.2.1 Machine Learning 4
     
    1.2.2 Artificial Neural Network 7
     
    1.2.3 Convolutional Neural Network 8
     
    1.2.4 Recurrent Neural Network 9
     
    1.2.5 Development of Deep Reinforcement Learning 10
     
    1.3 Potentials and Applications of DRL 11
     
    1.3.1 Benefits of DRL in Human Lives 11
     
    1.3.2 Features and Advantages of DRL Techniques 12
     
    1.3.3 Academic Research Activities 12
     
    1.3.4 Applications of DRL Techniques 13
     
    1.3.5 Applications of DRL Techniques in Wireless Networks 15
     
    1.4 Structure of this Book and Target Readership 16
     
    1.4.1 Motivations and Structure of this Book 16
     
    1.4.2 Target Readership 19
     
    1.5 Chapter Summary 20
     
    References 21
     
    2 Markov Decision Process and Reinforcement Learning 25
     
    2.1 Markov Decision Process 25
     
    2.2 Partially Observable Markov Decision Process 26
     
    2.3 Policy and Value Functions 29
     
    2.4 Bellman Equations 30
     
    2.5 Solutions of MDP Problems 31
     
    2.5.1 Dynamic Programming 31
     
    2.5.1.1 Policy Evaluation 31
     
    2.5.1.2 Policy Improvement 31
     
    2.5.1.3 Policy Iteration 31
     
    2.5.2 Monte Carlo Sampling 32
     
    2.6 Reinforcement Learning 33
     
    2.7 Chapter Summary 35
     
    References 35
     
    3 Deep Reinforcement Learning Models and Techniques 37
     
    3.1 Value-Based DRL Methods 37
     
    3.1.1 Deep Q-Network 38
     
    3.1.2 Double DQN 41
     
    3.1.3 Prioritized Experience Replay 42
     
    3.1.4 Dueling Network 44
     
    3.2 Policy-Gradient Methods 45
     
    3.2.1 REINFORCE Algorithm 46
     
    3.2.1.1 Policy Gradient Estimation 46
     
    3.2.1.2 Reducing the Variance 48
     
    3.2.1.3 Policy Gradient Theorem 50
     
    3.2.2 Actor-Critic Methods 51
     
    3.2.3 Advantage of Actor-Critic Methods 52
     
    3.2.3.1 Advantage of Actor-Critic (A2C) 53
     
    3.2.3.2 Asynchronous Advantage Actor-Critic (A3C) 55
     
    3.2.3.3 Generalized Advantage Estimate (GAE) 57
     
    3.3 Deterministic Policy Gradient (DPG) 59
     
    3.3.1 Deterministic Policy Gradient Theorem 59
     
    3.3.2 Deep Deterministic Policy Gradient (DDPG) 61
     
    3.3.3 Distributed Distributional DDPG (D4PG) 63
     
    3.4 Natural Gradients 63
     
    3.4.1 Principle of Natural Gradients 64
     
    3.4.2 Trust Region Policy Optimization (TRPO) 67
     
    3.4.2.1 Trust Region 69
     
    3.4.2.2 Sample-Based Formulation 70
     
    3.4.2.3 Practical Implementation 70
     
    3.4.3 Proximal Policy Optimization (PPO) 72
     
    3.5 Model-Based RL 74
     
    3.5.1 Vanilla Model-Based RL 75
     
    3.5.2 Robust Model-Based RL: Model-Ensemble TRPO (ME-TRPO) 76
     
    3.5.3 Adaptive Model-Based RL: Model-Based Meta-Policy Optimization (mb-mpo) 77
     
    3.6 Chapter Summary 78
     
    References 79
     
    4 A Case Study and Detailed Implementation 83
     
    4.1 System Model and Problem Formulation 83
     
    4.1.1 System Model and Assumptions 84
     
    4.1.1.1 Jamming Model 84
     
    4.1.1.2 System Operation 85
     
    4.1.2 Problem Formulation 86
     
    4.1.2.1 State Space 86
     
    4.1.2.2 Action Space 87
     
    4.1.2.3 Immediate Reward 88
     
    4.1.2.4 Optimization