Game Theory and Machine Learning in UAVs-Assisted Wireless Communication Networks: A Survey
arXiv:2108.03495
Abstract
In recent years, Unmanned Aerial Vehicles (UAVs) have been used in fields such as architecture, business delivery, military and civilian theaters, and many others. With increased applications comes the increased demand for advanced algorithms for resource allocation and energy management. As is well known, game theory and machine learning are two powerful tools already widely used in the wireless communication field and there are numerous surveys of game theory and machine learning usage in wireless communication. Existing surveys however focus either on game theory or machine learning and due to this fact, the current article surveys both game-theoretic and machine learning algorithms for use by UAVs in Wireless Communication Networks (U-WCNs). We also discuss how to combine game theory and machine learning for solving problems in U-WCNs and identify several future research directions.
References in corpus (13)
- Continuous control with deep reinforcement learning
- Federated Learning: Strategies for Improving Communication Efficiency
- Survey of Important Issues in UAV Communication Networks
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
- Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks
- Peer-to-peer Federated Learning on Graphs
- Deep Reinforcement Learning for Autonomous Driving
- Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach
- Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space
- Applications of Deep Reinforcement Learning in Communications and Networking: A Survey
- Mobile Unmanned Aerial Vehicles (UAVs) for Energy-Efficient Internet of Things Communications
- Survey on UAV Cellular Communications: Practical Aspects, Standardization Advancements, Regulation, and Security Challenges
- Massive UAV-to-Ground Communication and its Stable Movement Control: A Mean-Field Approach