# AlphaNIST trains a robot assembly policy in simulation > Researchers tested multi-step assembly using one reinforcement-learning policy with sparse rewards. - Canonical URL: https://newsverum.com/en/news/alphanist-trains-a-robot-policy-for-assembly-in-simulation - Publisher: Newsverum - Section: Technology - Country: United States - Published: 2026-10-13T00:51:40+00:00 - Updated: 2026-10-13T00:51:40+00:00 - Event / data period: 2026-10-09 - Other editions: [Türkçe](https://newsverum.com/tr/news/alphanist-trains-a-robot-policy-for-assembly-in-simulation.md), [العربية](https://newsverum.com/ar/news/alphanist-trains-a-robot-policy-for-assembly-in-simulation.md), [Français](https://newsverum.com/fr/news/alphanist-trains-a-robot-policy-for-assembly-in-simulation.md), [Español](https://newsverum.com/es/news/alphanist-trains-a-robot-policy-for-assembly-in-simulation.md), [Deutsch](https://newsverum.com/de/news/alphanist-trains-a-robot-policy-for-assembly-in-simulation.md), [Português](https://newsverum.com/pt/news/alphanist-trains-a-robot-policy-for-assembly-in-simulation.md) Researchers affiliated with NVIDIA and the University of Washington published AlphaNIST, a robotics learning study. It trains a single policy with PPO and sparse binary rewards on simulated assembly tasks, without demonstrations or manually tuned task-specific skill primitives. The paper reports 98.2% overall success across simulation training trials on ATB1 tasks. The researchers also show the policy learning some multi-component assembly sequences; however, this is simulation training success, not validation on a physical robot or evidence of real-world safety. ## Data ### Research result 20 ATB1 tasks; simulation training trials; no physical-robot test Methodology: The value is limited to the benchmark experiment reported in the paper; it is not a field result or general performance guarantee. | Measure | Percent | Scope | |---|---|---| | Overall task success in ATB1 simulation training | 98.2 | 20 ATB1 tasks; simulation training trials; no physical-robot test | Sources: · Download data: [JSON](https://newsverum.com/api/v1/articles/alphanist-trains-a-robot-policy-for-assembly-in-simulation/data/reported-result-1?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/alphanist-trains-a-robot-policy-for-assembly-in-simulation/data/reported-result-1?lang=en&format=csv) ## Sources - [arXiv preprint by NVIDIA and University of Washington researchers]() (Source checked: 2026-10-13; Published: 2026-10-09) --- Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)