# Towards Robust Deep Reinforcement Learning for Traffic Signal Control: Demand Surges, Incidents and Sensor Failures

## TL;DR

This paper develops a flexible framework to evaluate deep reinforcement learning traffic controllers under various uncertainties like demand surges, incidents, and sensor failures, providing insights for improving robustness in urban traffic management.

## Contribution

It introduces an open-source evaluation framework and offers new design strategies to enhance the robustness of deep RL traffic controllers against real-world uncertainties.

## Key findings

- Deep RL controllers' performance varies under different scenarios.
- Certain design modifications improve robustness against demand surges.
- Framework enables systematic testing of traffic control algorithms.

## Abstract

Reinforcement learning (RL) constitutes a promising solution for alleviating the problem of traffic congestion. In particular, deep RL algorithms have been shown to produce adaptive traffic signal controllers that outperform conventional systems. However, in order to be reliable in highly dynamic urban areas, such controllers need to be robust with the respect to a series of exogenous sources of uncertainty. In this paper, we develop an open-source callback-based framework for promoting the flexible evaluation of different deep RL configurations under a traffic simulation environment. With this framework, we investigate how deep RL-based adaptive traffic controllers perform under different scenarios, namely under demand surges caused by special events, capacity reductions from incidents and sensor failures. We extract several key insights for the development of robust deep RL algorithms for traffic control and propose concrete designs to mitigate the impact of the considered exogenous uncertainties.