NVIDIA's ADEPT Pre-trains Dexterity, Cuts Robot Task Learning Cost by 3x
KyleMorgenstein · x · 2026-08-22
NVIDIA introduced ADEPT, a pre-training and post-training paradigm that treats dexterity as a prior rather than a per-task cost. The system learns reach-grasp-reorient-transport once in simulation using RL, then post-trains specialists. These policies achieve zero-shot deployment on real robot hands using pixels and touch, requiring only 3B steps per new task compared to 9B from scratch.
Related event: NVIDIA Unveils ADEPT: Dexterity Pretraining Speeds Up Robot Learning by 3x(3 posts)→
More from Embodied
- SHOES: 10 minutes of real-robot RL lets quadrupeds walk in shoes, CoRL 2026 paper — kscottz · 2026-10-16
- Tesla Cybercab robotaxis logged zero crashes in first two weeks of public rides, NHTSA data shows — elonmusk · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- WEDGE paper generates training environments conditioned on navigation agent failures — _akhaliq · 2026-10-16
- Viral meme nails AI's irony: it can write symphonies but can't do the dishes — briannekimmel · 2026-10-16
- Knödel Watch: animated vocabulary cards on ESP32-S3, open-sourced 4 days after unboxing — alexcovo_eth · 2026-10-16