Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach

TL;DR

This paper introduces DTLight, a lightweight, offline-trained transformer-based traffic signal control method that outperforms existing online RL approaches and can be efficiently fine-tuned for real-world deployment.

Contribution

The paper presents DTLight, a novel lightweight transformer-based TSC method utilizing knowledge distillation and adapters for efficient offline training and online adaptation.

Findings

DTLight outperforms state-of-the-art online RL methods in synthetic and real-world scenarios.

Online fine-tuning of DTLight improves performance by up to 42.6%.

The approach reduces computational costs and enhances practicality for real-world traffic control.

Abstract

Efficient traffic signal control is critical for reducing traffic congestion and improving overall transportation efficiency. The dynamic nature of traffic flow has prompted researchers to explore Reinforcement Learning (RL) for traffic signal control (TSC). Compared with traditional methods, RL-based solutions have shown preferable performance. However, the application of RL-based traffic signal controllers in the real world is limited by the low sample efficiency and high computational requirements of these solutions. In this work, we propose DTLight, a simple yet powerful lightweight Decision Transformer-based TSC method that can learn policy from easily accessible offline datasets. DTLight novelly leverages knowledge distillation to learn a lightweight controller from a well-trained larger teacher model to reduce implementation computation. Additionally, it integrates adapter modules to mitigate the expenses associated with fine-tuning, which makes DTLight practical for online adaptation with minimal computation and only a few fine-tuning steps during real deployment. Moreover, DTLight is further enhanced to be more applicable to real-world TSC problems. Extensive experiments on synthetic and real-world scenarios show that DTLight pre-trained purely on offline datasets can outperform state-of-the-art online RL-based methods in most scenarios. Experiment results also show that online fine-tuning further improves the performance of DTLight by up to 42.6% over the best online RL baseline methods. In this work, we also introduce Datasets specifically designed for TSC with offline RL (referred to as DTRL). Our datasets and code are publicly available.