Login / Signup
On the Explainability and Expressiveness of Function Approximation Methods in RL-Based Traffic Signal Control.
Lincoln Vinicius Schreiber
Lucas Nunes Alegre
Ana L. C. Bazzan
Gabriel de Oliveira Ramos
Published in:
IJCNN (2022)
Keyphrases
</>
approximation methods
function approximators
traffic signal control
reinforcement learning
policy gradient
function approximation
temporal difference
reinforcement learning algorithms
learning tasks
action space
multi agent
neural network
image sequences
cooperative
search space
belief state