AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control

TL;DR

AttendLight is a universal reinforcement learning model for traffic signal control that adapts to any intersection configuration, outperforming existing methods on synthetic and real-world data.

Contribution

It introduces a universal RL model with dual attention mechanisms that generalizes across various intersection structures without retraining.

Findings

Outperforms classical and RL-based methods on benchmark datasets.

Works effectively across diverse intersection configurations.

Generalizes well in multi-environment training scenarios.

Abstract

We propose AttendLight, an end-to-end Reinforcement Learning (RL) algorithm for the problem of traffic signal control. Previous approaches for this problem have the shortcoming that they require training for each new intersection with a different structure or traffic flow distribution. AttendLight solves this issue by training a single, universal model for intersections with any number of roads, lanes, phases (possible signals), and traffic flow. To this end, we propose a deep RL model which incorporates two attention models. The first attention model is introduced to handle different numbers of roads-lanes; and the second attention model is intended for enabling decision-making with any number of phases in an intersection. As a result, our proposed model works for any intersection configuration, as long as a similar configuration is represented in the training set. Experiments were conducted with both synthetic and real-world standard benchmark data-sets. The results we show cover intersections with three or four approaching roads; one-directional/bi-directional roads with one, two, and three lanes; different number of phases; and different traffic flows. We consider two regimes: (i) single-environment training, single-deployment, and (ii) multi-environment training, multi-deployment. AttendLight outperforms both classical and other RL-based approaches on all cases in both regimes.