π0.5 finetuning on real manufacturing: 1 hour of clean data beat the previous 17

DominiqueCAPaul · x · 2026-09-24

A two-month ablation of π0.5 finetuning on a real manufacturing task, with all data and runs published. Final policy success rate: 98%.

Key findings:

Surprisingly unimportant: learning rate, batch size, relative vs. absolute joints, image augmentation.

Related event: Real-World π0.5 Fine-Tuning: Data Diversity Beats Scale, Hitting 98% Success(6 posts)→

Original post →

More from Embodied

Embodied channel →