We've trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand.
We've observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek.
We've trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
We're releasing eight simulated robotics environments and a Baselines implementation of Hindsight Experience Replay, all developed for our research over the past year. We've used these environments to train models which work on physical robots.
We've created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.