Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning

TL;DR

This paper introduces KS-DDPG, a multi-agent deep reinforcement learning approach with knowledge sharing for optimizing traffic signal control, demonstrating improved efficiency and faster convergence in large-scale networks.

Contribution

The paper presents a novel multi-agent reinforcement learning method with a communication protocol for enhanced traffic signal coordination.

Findings

KS-DDPG outperforms existing methods in large-scale traffic control.

The communication mechanism accelerates model convergence.

The approach adapts well to traffic flow fluctuations.

Abstract

Inefficient traffic control may cause numerous problems such as traffic congestion and energy waste. This paper proposes a novel multi-agent reinforcement learning method, named KS-DDPG (Knowledge Sharing Deep Deterministic Policy Gradient) to achieve optimal control by enhancing the cooperation between traffic signals. By introducing the knowledge-sharing enabled communication protocol, each agent can access to the collective representation of the traffic environment collected by all agents. The proposed method is evaluated through two experiments respectively using synthetic and real-world datasets. The comparison with state-of-the-art reinforcement learning-based and conventional transportation methods demonstrate the proposed KS-DDPG has significant efficiency in controlling large-scale transportation networks and coping with fluctuations in traffic flow. In addition, the introduced communication mechanism has also been proven to speed up the convergence of the model without significantly increasing the computational burden.