近年来，无人机（UAVs）已被用于建筑、商业交付、军事和民用战区等领域。随着应用的增加，对资源分配和能源管理的高级算法的需求也随之增加。众所周知，博弈论和机器学习是已经广泛应用于无线通信领域的两个强有力的工具，关于博弈论和机器学习在无线通信中的应用有很多研究。然而，现有的调查都集中在博弈论或机器学习，由于这一事实，目前的文章研究了在无线通信网络（U—WCNs）无人机中使用的博弈论和机器学习算法。本文还讨论了如何将博弈论和机器学习相结合来解决U—WCNs中的问题，并确定了未来的研究方向。

Preface
PART I FUNDAMENTALS OF GAME THEORY
CHAPTER 1 A Very Short Tour of Game Theory
1.1 Introduction
1.2 A Better Understanding of the Need for Game Theory from Four Simple Examples
1.3 Representations and Classification of Games
1.3.1 Representations of a Game
1.3.2 Classification of Games
1.4 Some Fundamental Notions of Game Theory
1.4.1 Actions, Pure Strategies, Mixed Strategies
1.4.2 Dominant Strategies, Rationality, Pareto-Dominance, Best-Response Correspondence
1.4.3 Nash Equilibrium, Dominant Strategy Equilibrium Correlated Equilibrium, Coarse Correlated Equilibrium
1.4.4 Ilustration of Some Concepts
1.5 More about the Scope of Game Theory
1.5.1 About Rationality
1.5.2 About Selfishness
1.5.3 About Interaction
1.5.4 About the Solution Concepts
CHAPTER 2 Playing with Equilibria in Wireless Non-Cooperative Games
2.1 Introduction
2.2 Equilibrium Existence
2.2.1 Better-Reply Secure and Quasi-Concave Games
2.2.2 Continuous Quasi-Concave Games
2.2.3 Potential Games
2.2.4 S-Modular Games
2.2.5 Recursive Diagonally Transferable Continuous Games
2.2.6 Existence of Mixed Nash Equilibria
2.2.7 A Note on the Existence of Nash Equilibria in Extensive-Form Games
2.2.8 Other Classes of Games Possessing at Least one Pure Nash Equilibrium
2.3 Equilibrium Uniqueness
2.3.1 The Best Responses Do Not Need to be Explicated
2.3.2 When the Best Responses Can be Explicated
2.4 Equilibrium Selection
2.4.1 Equilibrium Selection in Concave Games
2.4.2 The Role of Dynamics in Equilibrium Selection
2.4.3 Additional Comments
2.5 Equilibrium Efficiency
2.5.1 Measuring Equilibrium Efficiency
2.5.2 Improving Equilibrium Efficiency
2.6 Conclusion
CHAPTER 3 Moving from Static to Dynamic Games
3.1 Introduction
3.1.1 Informal Definition of a Dynamic Game
3.1.2 Classifying Dynamic Games
3.2 Repeated Games
3.2.1 Introduction
3.2.2 Fundamental Notions of Repeated Games
3.2.3 Equilibria in Repeated Games with Perfect Monitoring
3.2.4 Beyond the Perfect Monitoring Assumption
3.3 Stochastic Games
3.3.1 Stochastic Games with a Common State
3.3.2 Stochastic Games with Individual States
3.4 Difference Games and Differential Games
3.4.1 Difference Games with a Common State
3.4.2 Differential Games with a Common State
3.5 Evolutionary Games
3.5.1 Dynamic Procedures vs. Perfect Anticipation
3.5.2 Pairwise Interaction Model
3.5.3 Generic Formulation of Population Games
3.5.4 Evolutionary Game Dynamics
3.5.5 Price of Anarchy in Evolutionary Games
3.5.6 Applying Evolutionary Games to the Medium Access Control Problem
PART II GAMES WITH INCOMPLETE INFORMATION AND LEARNING
CHAPTER 4 Bayesian Games
4.1 Introduction
4.2 Bayesian Games in a Nutshell
4.2.1 The Harsanyi Model
4.2.2 Bayesian Equilibrium
4.3 Application to Power Control Games
4.3.1 Bayesian Energy-Efficient Power Control Games
4.3.2 Bayesian Rate Efficient Power Allocation Games
CHAPTER 5 Partially Distributed Learning Algorithms
5.1 Introduction
5.2 Best Response Dynamics
5.2.1 An Acyclic Graph Game has a Pure Equilibrium
5.2.2 Weakly Acyclic Games and BRD
5.3 Fictitious-Play-Based Algorithms
5.3.1 Brown's Fictitious Play Model
5.3.2 Other Versions of Fictitious Play
5.3.3 On the Convergence of Frequencies
5.3.4 Asynchronous Clocks in Stochastic Fictitious Play
5.3.5 Is Fictitious Play Applicable in Wireless Games
5.4 Learning Logit Equilibria
5.4.1 Information-Theoretic Interpretation of Boltzmann-Gibbs Rule
5.5 Games with Cost