English

V-Max: A Reinforcement Learning Framework for Autonomous Driving

Machine Learning 2025-07-18 v3 Artificial Intelligence Robotics

Abstract

Learning-based decision-making has the potential to enable generalizable Autonomous Driving (AD) policies, reducing the engineering overhead of rule-based approaches. Imitation Learning (IL) remains the dominant paradigm, benefiting from large-scale human demonstration datasets, but it suffers from inherent limitations such as distribution shift and imitation gaps. Reinforcement Learning (RL) presents a promising alternative, yet its adoption in AD remains limited due to the lack of standardized and efficient research frameworks. To this end, we introduce V-Max, an open research framework providing all the necessary tools to make RL practical for AD. V-Max is built on Waymax, a hardware-accelerated AD simulator designed for large-scale experimentation. We extend it using ScenarioNet's approach, enabling the fast simulation of diverse AD datasets.

Keywords

Cite

@article{arxiv.2503.08388,
  title  = {V-Max: A Reinforcement Learning Framework for Autonomous Driving},
  author = {Valentin Charraut and Waël Doulazmi and Thomas Tournaire and Thibault Buhet},
  journal= {arXiv preprint arXiv:2503.08388},
  year   = {2025}
}

Comments

RLC 25 - Camera-ready

R2 v1 2026-06-28T22:15:47.689Z