First in thousands of parallel simulations, then in the real world: The robot arm of OpenAI can already solve a magic cube with one hand. He is controlled by software that has taught the process itself. Still, this is still a challenge in the real world.
Researchers of the AI initiative OpenAI have developed a robotic arm that can handle various fine motor tasks. A first success: The machine has a Rubik’s Cube – also called magic cube – solved with one hand and independently. The basis is a machine learning program based on the principle of Reinforcement Learning. This controls the fingers and joints of the hand.
In order to achieve this, the researchers faced a challenge: how can software virtually practice parallel solution approaches? For this purpose, a virtual environment was programmed that simulates the physical laws of physics. There, a model of the robot hand and its sensors is used. Such environments can then run in parallel thousands of times. The program learns so much faster, how to deal with the magic cube.