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

by   Zhenning Li, et al.

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.



page 18

page 26


A Deep Reinforcement Learning Approach for Traffic Signal Control Optimization

Inefficient traffic signal control methods may cause numerous problems, ...

CoLight: Learning Network-level Cooperation for Traffic Signal Control

Cooperation is critical in multi-agent reinforcement learning (MARL). In...

Multi-Agent Reinforcement Learning for Traffic Signal Control through Universal Communication Method

How to coordinate the communication among intersections effectively in r...

Deep Deterministic Policy Gradient for Urban Traffic Light Control

Traffic light timing optimization is still an active line of research de...

Objective-aware Traffic Simulation via Inverse Reinforcement Learning

Traffic simulators act as an essential component in the operating and pl...

Multi-agent control of airplane wing stability under the flexural torsion flutter

This paper proposes a novel method for prevention of the increasing osci...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.