Skip to content
arXiv Robotics — research abstracts· Wenzhan Li, Yiran Qin, Heng Zhou, Huirui Wang, Yulan Guo, Ruimao Zhang·· 5 days agoEditorial score60

Trust-Calibrated VLA Policy Post-Training with Evolving Imagination

Trust-Calibrated VLA Policy Post-Training with Evolving Imagination

Summary

This research proposes MERL, a framework that couples policy optimization with an online-updated simulator to refine VLA models post-training. The method balances reliability and efficiency by controlling the ratio of imagined data and rollout horizon based on simulator reliability. It also uses chunk-level trust to guide replay selection and optimization. MERL achieves 79.7% average success on perturbed LIBERO-PRO tasks and 80.0% on physical-robot tasks with 50 demonstrations per task.

Source: arXiv Robotics — research abstracts · Read original article ↗

Loading article text…

Source：arXiv Robotics — research abstracts · arxiv.org

#Model release#Research#Reinforcement learning#VLA#Imitation learning#Sim-to-real
Timezone · UTC

Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).