Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Control

TL;DR

This paper introduces LemgoRL, a realistic simulation benchmark for training reinforcement learning agents in traffic signal control, bridging the gap between simplified models and real-world deployment, and demonstrating its effectiveness with state-of-the-art algorithms.

Contribution

The paper presents LemgoRL, a realistic traffic simulation benchmark with regulatory compliance, enabling RL research for real-world traffic signal control deployment.

Findings

LemgoRL effectively simulates real-world traffic scenarios.

State-of-the-art Deep RL algorithms perform well on LemgoRL.

Benchmark facilitates development of RL methods for practical traffic management.

Abstract

Sub-optimal control policies in intersection traffic signal controllers (TSC) contribute to congestion and lead to negative effects on human health and the environment. Reinforcement learning (RL) for traffic signal control is a promising approach to design better control policies and has attracted considerable research interest in recent years. However, most work done in this area used simplified simulation environments of traffic scenarios to train RL-based TSC. To deploy RL in real-world traffic systems, the gap between simplified simulation environments and real-world applications has to be closed. Therefore, we propose LemgoRL, a benchmark tool to train RL agents as TSC in a realistic simulation environment of Lemgo, a medium-sized town in Germany. In addition to the realistic simulation model, LemgoRL encompasses a traffic signal logic unit that ensures compliance with all regulatory and safety requirements. LemgoRL offers the same interface as the wellknown OpenAI gym toolkit to enable easy deployment in existing research work. To demonstrate the functionality and applicability of LemgoRL, we train a state-of-the-art Deep RL algorithm on a CPU cluster utilizing a framework for distributed and parallel RL and compare its performance with other methods. Our benchmark tool drives the development of RL algorithms towards real-world applications.