Actor-Critic Deep Reinforcement Learning for Energy Minimization in UAV-Aided Networks.
Yaxiong YuanLei LeiThang X. VuSymeon ChatzinotasBjörn E. OtterstenPublished in: EuCNC (2020)
Keyphrases
- energy minimization
- actor critic
- reinforcement learning
- energy function
- graph cuts
- temporal difference
- optimal control
- policy gradient
- approximate dynamic programming
- reinforcement learning algorithms
- function approximation
- markov random field
- neuro fuzzy
- gradient method
- state space
- policy iteration
- belief propagation
- image segmentation
- markov decision processes
- policy gradient methods
- evaluation function
- step size
- graphical models
- model free
- action selection
- computer vision
- markov decision process
- dynamic environments
- reinforcement learning methods
- dynamic programming
- cost function
- control system
- image processing