Introduction

This book presents reinforcement learning (RL) based solutions for user-centric online network selection optimization. The main content can be divided into three parts.

Part 1: Learning the Best Network

The first part (chapter 2 and 3) focuses on how to learn the best network when QoE is revealed beyond QoS under the framework of multi-armed bandit (MAB).

Part 2: Meeting Dynamic User Demand

The second part (chapter 4 and 5) focuses on how to meet dynamic user demand in complex and uncertain heterogeneous wireless networks under the framework of markov decision process (MDP).

Part 3: Handling Multiple Users in Large-Scale Networks

The third part (chapter 6 and 7) focuses on how to meet heterogeneous user demand for multiple users in large-scale networks under the framework of game theory.

Additional Information

Efficient RL algorithms with practical constraints and considerations are proposed to optimize QoE for realizing intelligent online network selection for future mobile networks. This book is intended as a reference resource for researchers and designers in resource management of 5G networks and beyond.