RT Journal Article
A1 I. Arel
A1 C. Liu
A1 T. Urbanik
A1 A.G. Kohls

PB iet
T1 Reinforcement learning-based multi-agent system for network traffic signal control
JN IET Intelligent Transport Systems
VO 4
IS 2
SP 128
OP 135
AB A challenging application of artificial intelligence systems involves the scheduling of traffic signals in multi-intersection vehicular networks. This paper introduces a novel use of a multi-agent system and reinforcement learning (RL) framework to obtain an efficient traffic signal control policy. The latter is aimed at minimising the average delay, congestion and likelihood of intersection cross-blocking. A five-intersection traffic network has been studied in which each intersection is governed by an autonomous intelligent agent. Two types of agents, a central agent and an outbound agent, were employed. The outbound agents schedule traffic signals by following the longest-queue-first (LQF) algorithm, which has been proved to guarantee stability and fairness, and collaborate with the central agent by providing it local traffic statistics. The central agent learns a value function driven by its local and neighbours' traffic conditions. The novel methodology proposed here utilises the Q-Learning algorithm with a feedforward neural network for value function approximation. Experimental results clearly demonstrate the advantages of multi-agent RL-based control over LQF governed isolated single-intersection control, thus paving the way for efficient distributed traffic signal control in complex settings.
K1 reinforcement learning-based multi-agent system
K1 network traffic signal control
K1 multiintersection vehicular networks
K1 local traffic statistics
K1 Q-Learning algorithm
K1 feedforward neural network
K1 longest-queue-first algorithm
K1 traffic signal scheduling
DO https://doi.org/10.1049/iet-its.2009.0070
UL https://digital-library.theiet.org/;jsessionid=5br27917r46jo.x-iet-live-01content/journals/10.1049/iet-its.2009.0070
LA English
SN 1751-956X
YR 2010
OL EN