An efficient actor-critic reinforcement learning for device-to-device communication underlaying sectored cellular network.
Pratap KhuntiaRanjay HazraPeter H. J. ChongPublished in: Int. J. Commun. Syst. (2020)
Keyphrases
- reinforcement learning
- actor critic
- cellular networks
- function approximation
- data acquisition
- temporal difference
- machine learning
- policy gradient
- markov decision processes
- reinforcement learning algorithms
- state space
- approximate dynamic programming
- learning algorithm
- mobile networks
- optimal control
- multi agent
- wireless networks
- low cost
- base station
- model free
- real time
- dynamic programming