ExToken: Structured Exploration Boosts Sample Efficiency for Vision-Language-Action RL

Jul 15, 2026

Researchers present ExToken, a framework that conditions vision-language-action (VLA) reinforcement learning policies on discrete behavioral priors derived from offline demonstrations. By encouraging exploration of diverse trajectory modes, ExToken addresses exploration stagnation and improves sample efficiency, leading to faster convergence and better task performance in both simulated and real-world robotic manipulation tasks, especially under limited interaction budgets.

Why it matters: Improving sample efficiency in VLA reinforcement learning could reduce the cost and time required to train robotic systems, facilitating broader real-world deployment.

Full story at: arXiv Robotics ↗