A Distributed Policy Gradient Algorithm for Optimal Coordination of Mobile Sensor Networks.

Jing Wang Khanh Pham

Published in: IEEE SENSORS (2022)

Keyphrases

mobile sensor networks
dynamic programming
optimal solution
learning algorithm
worst case
cost function
computational complexity
multi agent
sensor networks
gradient ascent
np hard
policy gradient
objective function
neural network
search space
cooperative
monte carlo
average reward