A Realization of Fog-RAN Slicing via Deep Reinforcement Learning.
Hongyu XiangShi YanMugen PengPublished in: IEEE Trans. Wirel. Commun. (2020)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- model free
- state space
- optimal policy
- machine learning
- temporal difference
- weather conditions
- single image
- reinforcement learning algorithms
- action space
- control problems
- learning process
- robotic control
- temporal difference learning
- control policy
- database
- program slicing
- partially observable
- action selection
- multi agent
- learning algorithm
- neural network