Suchen und Finden
Service
Deep Reinforcement Learning for Wireless Networks
F. Richard Yu, Ying He
Verlag Springer-Verlag, 2019
ISBN 9783030105464 , 78 Seiten
Format PDF, OL
Kopierschutz Wasserzeichen
Geräte
Preface
6
A Brief Journey Through ``Deep Reinforcement Learning for Wireless Networks''
6
Contents
8
1 Introduction to Machine Learning
10
1.1 Supervised Learning
10
1.1.1 k-Nearest Neighbor (k-NN)
11
1.1.2 Decision Tree (DT)
11
1.1.3 Random Forest
12
1.1.4 Neural Network (NN)
14
Random NN
14
Deep NN
15
Convolutional NN
15
Recurrent NN
15
1.1.5 Support Vector Machine (SVM)
16
1.1.6 Bayes' Theory
16
1.1.7 Hidden Markov Models (HMM)
18
1.2 Unsupervised Learning
18
1.2.1 k-Means
18
1.2.2 Self-Organizing Map (SOM)
19
1.3 Semi-supervised Learning
20
References
20
2 Reinforcement Learning and Deep Reinforcement Learning
23
2.1 Reinforcement Learning
23
2.2 Deep Q-Learning
24
2.3 Beyond Deep Q-Learning
25
2.3.1 Double DQN
25
2.3.2 Dueling DQN
26
References
26
3 Deep Reinforcement Learning for Interference Alignment Wireless Networks
28
3.1 Introduction
28
3.2 System Model
30
3.2.1 Interference Alignment
30
3.2.2 Cache-Equipped Transmitters
31
3.3 Problem Formulation
32
3.3.1 Time-Varying IA-Based Channels
32
3.3.2 Formulation of the Network's Optimization Problem
33
System State
34
System Action
35
Reward Function
35
3.4 Simulation Results and Discussions
38
3.4.1 TensorFlow
39
3.4.2 Simulation Settings
40
3.4.3 Simulation Results and Discussions
42
3.5 Conclusions and Future Work
49
References
50
4 Deep Reinforcement Learning for Mobile Social Networks
52
4.1 Introduction
52
4.1.1 Related Works
54
4.1.2 Contributions
55
4.2 System Model
56
4.2.1 System Description
56
4.2.2 Network Model
57
4.2.3 Communication Model
58
4.2.4 Cache Model
59
4.2.5 Computing Model
60
4.3 Social Trust Scheme with Uncertain Reasoning
61
4.3.1 Trust Evaluation from Direct Observations
62
4.3.2 Trust Evaluation from Indirect Observations
63
Belief Function
64
Dempster's Rule of Combining Belief Functions
65
4.4 Problem Formulation
66
4.4.1 System State
66
4.4.2 System Action
67
4.4.3 Reward Function
68
4.5 Simulation Results and Discussions
69
4.5.1 Simulation Settings
70
4.5.2 Simulation Results
71
4.6 Conclusions and Future Work
75
References
76
Shop