Deep Reinforcement Learning Based Dynamic Trajectory Control for UAV-assisted Mobile Edge Computing.
Liang WangKezhi WangCunhua PanWei XuNauman AslamArumugam NallanathanPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- dynamic environments
- control problems
- unmanned aerial vehicles
- optimal control
- edge detection
- mobile devices
- robot control
- mobile phone
- adaptive control
- function approximation
- control strategies
- mobile learning
- control system
- control strategy
- control algorithm
- edge information
- markov decision processes
- action selection
- human operators
- learning process
- spatio temporal
- control policy