RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehicles
This work addresses route optimization for autonomous vehicles in transportation systems, but it appears incremental as it builds on existing MARL and traffic simulation methods without claiming major breakthroughs.
The authors tackled the problem of developing efficient route choice strategies for autonomous vehicles in urban environments by introducing RouteRL, a multi-agent reinforcement learning framework integrated with microscopic traffic simulation, which simulates daily route choices of both human drivers and AVs to optimize policies for predefined objectives.
RouteRL is a novel framework that integrates multi-agent reinforcement learning (MARL) with a microscopic traffic simulation, facilitating the testing and development of efficient route choice strategies for autonomous vehicles (AVs). The proposed framework simulates the daily route choices of driver agents in a city, including two types: human drivers, emulated using behavioral route choice models, and AVs, modeled as MARL agents optimizing their policies for a predefined objective. RouteRL aims to advance research in MARL, transport modeling, and human-AI interaction for transportation applications. This study presents a technical report on RouteRL, outlines its potential research contributions, and showcases its impact via illustrative examples.