Login / Signup
Deep Deterministic Policy Gradient for Urban Traffic Light Control.
Noe Casas
Published in:
CoRR (2017)
Keyphrases
</>
policy gradient
actor critic
parametric optimization
function approximation
gradient method
optimal control
reinforcement learning
model free reinforcement learning
approximation methods
urban areas
reinforcement learning algorithms
partially observable markov decision processes
traffic congestion
traffic light