V-Max: A Reinforcement Learning Framework for Autonomous Driving

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Charraut, Valentin, Doulazmi, Waël, Tournaire, Thomas, Buhet, Thibault
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911061736685568
author Charraut, Valentin
Doulazmi, Waël
Tournaire, Thomas
Buhet, Thibault
author_facet Charraut, Valentin
Doulazmi, Waël
Tournaire, Thomas
Buhet, Thibault
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08388
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle V-Max: A Reinforcement Learning Framework for Autonomous Driving
Charraut, Valentin
Doulazmi, Waël
Tournaire, Thomas
Buhet, Thibault
Machine Learning
Artificial Intelligence
Robotics
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.
title V-Max: A Reinforcement Learning Framework for Autonomous Driving
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2503.08388