Traffic-Aware UAV Placement Using a Generalizable Deep Reinforcement Learning Methodology.
Eduardo Nuno AlmeidaRui CamposManuel RicardoPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- path planning
- multi agent
- learning process
- unmanned aerial vehicles
- optimal policy
- function approximation
- road network
- network traffic
- action selection
- state space
- machine learning
- transfer learning
- control algorithm
- traffic flow
- design methodology
- supervised learning
- robotic control
- vision based navigation