Dynamic Antenna Control for HAPS Using Mean Field Reinforcement Learning in Multi-Cell Configuration.

Siyuan Yang Mondher Bouazizi Tomoaki Ohtsuki

Published in: ICC (2023)

Keyphrases

reinforcement learning
control problems
control system
optimal control
dynamic environments
control policy
robot control
closed form
em algorithm
control strategies
closed loop
control strategy
adaptive control
reinforcement learning algorithms
markov random field
multi agent
neural network