V-Max: A Reinforcement Learning Framework for Autonomous Driving

Valentin Charraut, Waël Doulazmi, Thomas Tournaire, Thibault Buhet
3/11/2025
cs.LGcs.AIcs.RO

No official code found. Best implementation: valeoai/V-Max (155 stars, last commit 2025-10-21).

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.

View on arXivView PDF

Code Implementations(1)

valeoai/V-MaxCommunity100%

Plug-and-play extension of the Waymax simulator.

15525PythonJan 6, 20251 years agoNOASSERTION

Similar Papers

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

88% match2026

Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors

87% match1 repo1082023

Scenario-Based Hierarchical Reinforcement Learning for Automated Driving Decision Making

86% match2025

Bootstrapping Reinforcement Learning with Sub-optimal Policies for Autonomous Driving

86% match2025

From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning

86% match2025

MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning

86% match1 repo2662025

Cite this paper

@article{charraut2025vmax,
  title  = {V-Max: A Reinforcement Learning Framework for Autonomous Driving},
  author = {Valentin Charraut and Waël Doulazmi and Thomas Tournaire and Thibault Buhet},
  year   = {2025},
  eprint = {2503.08388},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.08388v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2503.08388.svg)](https://codeofpaper.com/paper/2503.08388)

Discussion