Deep Reinforcement Learning for Intelligent Transportation Systems

TL;DR

This paper investigates the application of Deep Q-Networks to optimize traffic light control in intelligent transportation systems, demonstrating their ability to learn effective policies and emergent traffic management behaviors.

Contribution

It introduces the use of DQN for scalable traffic light control, showing their capacity to learn thresholding policies and emergent greenwave patterns in multi-intersection networks.

Findings

DQN algorithms learn thresholding policies at single intersections.

DQN demonstrates scalability and emergent greenwave patterns.

DQN produces intelligent traffic light behaviors in complex networks.

Abstract

Intelligent Transportation Systems (ITSs) are envisioned to play a critical role in improving traffic flow and reducing congestion, which is a pervasive issue impacting urban areas around the globe. Rapidly advancing vehicular communication and edge cloud computation technologies provide key enablers for smart traffic management. However, operating viable real-time actuation mechanisms on a practically relevant scale involves formidable challenges, e.g., policy iteration and conventional Reinforcement Learning (RL) techniques suffer from poor scalability due to state space explosion. Motivated by these issues, we explore the potential for Deep Q-Networks (DQN) to optimize traffic light control policies. As an initial benchmark, we establish that the DQN algorithms yield the "thresholding" policy in a single-intersection. Next, we examine the scalability properties of DQN algorithms and their performance in a linear network topology with several intersections along a main artery. We demonstrate that DQN algorithms produce intelligent behavior, such as the emergence of "greenwave" patterns, reflecting their ability to learn favorable traffic light actuations.