← Back to Benchmarks
simmediumimitationmetric · varies

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

Description

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. To overcome this limitation, we pro

Source

http://arxiv.org/abs/2512.13636v3