Multi-agent reinforcement learning based 3D trajectory design in aerial-terrestrial wireless caching networks

Keyphrases

• Learning-based 100%
• UAV 100%
• Mobile Edge Caching 100%
• Multi-agent Reinforcement Learning 100%
• Aerial 100%
• 3D Trajectory Planning 100%
• Cache Performance 66%
• D2D Caching 50%
• Network Throughput 33%
• Network Topology 16%
• Storage Capacity 16%
• Mobile Users 16%
• High Mobility 16%
• Dynamic Environment 16%
• Caching 16%
• Wireless Devices 16%
• User Device 16%
• Mobility Patterns 16%
• Vehicle Trajectory 16%
• Multi-UAV 16%
• Device-to-device 16%
• Flying Base Station 16%
• In-network Caching 16%
• Backhaul 16%
• Learning-based Framework 16%
• Q-learning Algorithm 16%
• Multi-agent Q-learning 16%
• Flexible Deployment 16%
• Cache Storage 16%
• 3D Trajectory 16%
• Term Network 16%
• Popular Content 16%

Computer Science

• Multi-Agent Reinforcement Learning 100%
• Unmanned Aerial Vehicle 100%
• Network Topology 14%
• Learning Algorithm 14%
• Dynamic Environment 14%
• Wireless Device 14%
• Storage Capacity 14%
• multi agent 14%
• Device-To-Device 14%
• Cache Storage 14%
• Multiple Method 14%