In a blog post, the company said Eureka, which autonomously writes reward algorithms, has, for the first time, trained a robotic hand to perform rapid pen-spinning tricks as well as a human can.

Eureka has taught robots to open drawers and cabinets, toss and catch balls, search for Sarah Conner and manipulate scissors, among nearly 30 tasks.

Nvidia senior director of AI research, Anima Anandkumar, said reinforcement learning has enabled impressive wins over the last decade. Yet, many challenges still exist, such as reward design, which remains a trial-and-error process.

"Eureka is a first step toward developing new algorithms that integrate generative and reinforcement learning methods to solve hard tasks."