Solving Rubik’s Cube with a robot hand

OpenAI · 7 years ago · 42

A robot hand trained with neural networks and reinforcement learning can solve a Rubik's Cube and adapt to unexpected interference like being poked by objects. The system was trained entirely in simulation using a technique called Automatic Domain Randomization, which allows it to handle situations absent from training data. This demonstrates that reinforcement learning can transfer from virtual environments to physical manipulation tasks requiring fine motor control.