Dissipating stop-and-go waves in closed and open networks via deep reinforcement learning.

Abdul Rahman Kreidieh Cathy Wu Alexandre M. Bayen

Published in: ITSC (2018)

Keyphrases

reinforcement learning
social networks
function approximation
markov decision processes
state space
network structure
model free
reinforcement learning algorithms
network size
data mining
learning algorithm
complex networks
optimal control
network analysis
telecommunication networks
network topologies