Pressure releasing policy in traffic signal control with finite queue capacities.

Nan Xiao Emilio Frazzoli Yitong Li Yu Wang Danwei Wang

Published in: CDC (2014)

Keyphrases

traffic signal control
state dependent
optimal policy
steady state
queue length
multi objective
markov chain
real time
genetic algorithm
reinforcement learning
markov decision processes
finite number
infinite horizon
arrival rate