An Efficient Deep Reinforcement Learning Model for Urban Traffic Control

TL;DR

This paper introduces a novel deep reinforcement learning algorithm for urban traffic control that efficiently manages multiple intersections, adapting to complex traffic patterns and outperforming traditional methods in simulations.

Contribution

The paper presents an improved DRL algorithm that relaxes fixed traffic demand assumptions and reduces manual parameter tuning for urban traffic management.

Findings

Outperforms traditional rule-based traffic control methods.

Handles complex, real-world traffic scenarios effectively.

Reduces human intervention in parameter tuning.

Abstract

Urban Traffic Control (UTC) plays an essential role in Intelligent Transportation System (ITS) but remains difficult. Since model-based UTC methods may not accurately describe the complex nature of traffic dynamics in all situations, model-free data-driven UTC methods, especially reinforcement learning (RL) based UTC methods, received increasing interests in the last decade. However, existing DL approaches did not propose an efficient algorithm to solve the complicated multiple intersections control problems whose state-action spaces are vast. To solve this problem, we propose a Deep Reinforcement Learning (DRL) algorithm that combines several tricks to master an appropriate control strategy within an acceptable time. This new algorithm relaxes the fixed traffic demand pattern assumption and reduces human invention in parameter tuning. Simulation experiments have shown that our method outperforms traditional rule-based approaches and has the potential to handle more complex traffic problems in the real world.