Mitigating Partial Observability in Adaptive Traffic Signal Control with Transformers

TL;DR

This paper introduces Transformer-based controllers for adaptive traffic signal control to effectively handle partial observability, resulting in improved traffic flow and coordination in urban transportation systems.

Contribution

It presents a novel integration of Transformer architectures into ATSC systems to address partial observability challenges, enhancing policy learning and coordination.

Findings

Transformer models capture significant historical information.

Improved traffic flow and coordination in real-world scenarios.

Enhanced training efficiency and effectiveness.

Abstract

Efficient traffic signal control is essential for managing urban transportation, minimizing congestion, and improving safety and sustainability. Reinforcement Learning (RL) has emerged as a promising approach to enhancing adaptive traffic signal control (ATSC) systems, allowing controllers to learn optimal policies through interaction with the environment. However, challenges arise due to partial observability (PO) in traffic networks, where agents have limited visibility, hindering effectiveness. This paper presents the integration of Transformer-based controllers into ATSC systems to address PO effectively. We propose strategies to enhance training efficiency and effectiveness, demonstrating improved coordination capabilities in real-world scenarios. The results showcase the Transformer-based model's ability to capture significant information from historical observations, leading to better control policies and improved traffic flow. This study highlights the potential of leveraging the advanced Transformer architecture to enhance urban transportation management.