A Methodology for the Development of RL-Based Adaptive Traffic Signal Controllers

TL;DR

This paper introduces a comprehensive methodology for developing, deploying, and evaluating reinforcement learning-based adaptive traffic signal controllers, aiming to standardize approaches and improve comparability across studies.

Contribution

It provides a structured, step-by-step methodology covering all development phases, addressing current literature's lack of standardization.

Findings

Methodology improves comparability of RL traffic controllers.

Application to simple scenarios demonstrates its effectiveness.

Addresses limitations in existing research approaches.

Abstract

This article proposes a methodology for the development of adaptive traffic signal controllers using reinforcement learning. Our methodology addresses the lack of standardization in the literature that renders the comparison of approaches in different works meaningless, due to differences in metrics, environments, and even experimental design and methodology. The proposed methodology thus comprises all the steps necessary to develop, deploy and evaluate an adaptive traffic signal controller -- from simulation setup to problem formulation and experimental design. We illustrate the proposed methodology in two simple scenarios, highlighting how its different steps address limitations found in the current literature.