AI beats humans for the first time in physical skill game

Key Takeaways:

– Researchers at ETH Zurich have created an AI robot named CyberRunner to learn how to play the labyrinth maze game.
– The robot is equipped with two motors, a camera, and a computer, allowing it to play the game like a human.
– CyberRunner learns through experience using model-based reinforcement learning, making decisions and predicting outcomes.
– The robot makes observations, receives rewards, and keeps a memory of collected experience to improve its performance.
– CyberRunner set a new world record in the game, completing it in 14.48 seconds, beating the previous record by over 6%.
– The robot discovered shortcuts and ways to cheat, which researchers had to instruct it not to do.
– The research paper is available online and the project will be open-sourced.
– The researchers believe that CyberRunner is an ideal testbed for real-world machine learning and AI research.
– The project allows for large-scale experiments and citizen science.

The Next Web:

AI’s ability to beat human players in games like chess and GO is no longer surprising. After all, artificial intelligence has proved it can outperform its animate creators in certain tasks, especially when it comes to processing and analysing information. But physical skill has remained a human prerogative — until now.

Researchers at ETH Zurich have created an AI robot with the task to learn how to play the popular labyrinth maze game. The goal of the game is simple: using two knobs, you have to steer a marble ball from a start to an end point without it falling into the holes across the board.

But if you’ve ever played it, you know it’s actually quite challenging. The scientific explanation behind its difficulty is that it requires acute motor skills, spatial reasoning abilities — and a lot of practice.

The robot, named CyberRunner, is equipped with two motors (its hands), a camera (its eyes), and a computer (its brain), allowing it to play the game just like a person would.