Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning

TL;DR

This paper explores whether ChatGPT can assist novices in solving complex mixed traffic control problems in ITS, showing mixed results with significant improvements in some scenarios but not all.

Contribution

It demonstrates that ChatGPT can significantly enhance novice performance in certain traffic control environments, highlighting its potential as an assistive tool in ITS.

Findings

ChatGPT increases successful policies by 150% in intersection scenarios.

ChatGPT improves performance by 136% in bottleneck scenarios.

Some ChatGPT solutions outperform expert solutions.

Abstract

The surge in Reinforcement Learning (RL) applications in Intelligent Transportation Systems (ITS) has contributed to its growth as well as highlighted key challenges. However, defining objectives of RL agents in traffic control and management tasks, as well as aligning policies with these goals through an effective formulation of Markov Decision Process (MDP), can be challenging and often require domain experts in both RL and ITS. Recent advancements in Large Language Models (LLMs) such as GPT-4 highlight their broad general knowledge, reasoning capabilities, and commonsense priors across various domains. In this work, we conduct a large-scale user study involving 70 participants to investigate whether novices can leverage ChatGPT to solve complex mixed traffic control problems. Three environments are tested, including ring road, bottleneck, and intersection. We find ChatGPT has mixed results. For intersection and bottleneck, ChatGPT increases number of successful policies by 150% and 136% compared to solely beginner capabilities, with some of them even outperforming experts. However, ChatGPT does not provide consistent improvements across all scenarios.