Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking.

Arthur Müller Matthia Sabatelli

Published in: CoRR (2022)

Keyphrases

traffic signal control
reinforcement learning
action selection
action space
state space
dynamic programming
optimal policy
multi objective
multi agent
real time
optimal control
learning algorithm
machine learning
markov decision processes
human actions
objective function
traffic signal
agent learns