# SuperMimic cuts GPU hours for humanoid full-body control training by over 1,000x

- Source: Pieter Abbeel
- Published: 2026-10-21T16:55:23.000Z
- RoboHot: https://robohot.news/en/items/xkt82ek4n0n13f0r0zhjy28fc
- Original: https://x.com/pabbeel/status/2112950889808097708

## Summary

SuperMimic trains a humanoid full-body control policy on 129,514 motions, surpassing the previous best result of 128 GPUs over 7 days with 1 GPU in 3 hours, reducing GPU hours by over 1,000x. Pieter Abbeel shared it and called it a game changer, noting that the key lies in using a world model faster than conventional simulation and in collecting far more signal than policy gradients through backpropagation through time. The project page is https://supermimic.github.io, and the demo is at https://supermimic.github.io/demo/.