Mean Field Deep Reinforcement Learning for Fair and Efficient UAV Control.

Dezhi Chen Qi Qi Zirui Zhuang Jingyu Wang Jianxin Liao Zhu Han

Published in: IEEE Internet Things J. (2021)

Keyphrases

reinforcement learning
control problems
control system
optimal control
path planning
control strategies
learning algorithm
dynamic environments
em algorithm
markov chain
objective function
state space
pairwise
multi agent systems
belief networks
multi agent
model free
adaptive control
neural network
robot control