A Continuous Actor-Critic Deep Q-Learning-Enabled Deployment of UAV Base Stations: Toward 6G Small Cells in the Skies of Smart Cities.
Nahid ParvareshBurak KantarciPublished in: IEEE Open J. Commun. Soc. (2023)
Keyphrases
- learning problems
- reinforcement learning
- actor critic
- base station
- learning algorithm
- function approximation
- reinforcement learning algorithms
- smart cities
- learning tasks
- policy gradient
- temporal difference
- policy iteration
- wireless sensor networks
- wireless networks
- model free
- machine learning
- approximate dynamic programming
- multi agent
- neuro fuzzy
- state space
- world wide
- markov decision processes
- sensor networks
- smart city
- ad hoc networks
- communication networks
- mobile users
- action space
- monte carlo
- digital libraries
- gradient method
- dynamic environments
- optimal control
- service integration
- end users