Joint Optimization of Trajectory and Task Offloading Based on Deep Deterministic Policy Gradient in UAV-Assisted MEC.
Qisheng TanJielin FuPublished in: ICCT (2023)
Keyphrases
- joint optimization
- policy gradient
- reinforcement learning
- sparse representation
- function approximation
- gradient method
- optimal control
- path planning
- reinforcement learning algorithms
- variance reduction
- approximation methods
- control algorithm
- single agent
- partially observable markov decision processes
- dynamic environments
- average reward
- dynamic programming
- computational complexity
- pattern recognition