SOURCE-LINKED INTELLIGENCE

Aligning Multi-Trajectory Supervision with Policy Optimization for VLA Driving

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Vision-language-action (VLA) driving methods increasingly combine multi-trajectory imitation learning with group-relative policy optimization (GRPO), making trajectory selection critical to final performance. However, some high-scoring trajectories that improve imitation can degrade subsequent GRPO by inducing advantage estimates misaligned with the current policy's feasible behavior distribution, driving updates away from safe and compliant behaviors. To address this, we propose a novel framework that aligns multi-trajectory supervision with policy optimization. To address the policy gradient

Read original source ↗ Open in workspace

recordType

paper

region

Global