Deep Reinforcement Learning Aided Online Trajectory Optimization of Cellular-Connected UAVs with Offline Map Reconstruction.
Qing HaoHaitao ZhaoHao HuangGuan GuiTomoaki OhtsukiFumiyuki AdachiPublished in: VTC2023-Spring (2023)
Keyphrases
- reinforcement learning
- real time
- maximum a posteriori probability
- maximum a posteriori
- optimization process
- online learning
- image reconstruction
- control algorithm
- optimization problems
- cellular automata
- optimization method
- global optimization
- learning process
- function approximation
- dynamic environments
- learning problems
- multi agent
- constrained optimization
- joint optimization
- aerial vehicles
- optimization algorithm
- markov decision processes
- particle swarm optimization
- state space
- multi objective
- spatio temporal
- three dimensional
- learning algorithm
- neural network