AI Outmaneuvers Humans in Physical Skill Game for the First Time!

Researchers at ETH Zurich have created an AI robot named CyberRunner that can learn how to play the labyrinth maze game through experience-based model-based reinforcement learning. The robot is equipped with two motors, a camera, and a computer, allowing it to play the game similarly to a human. During the learning process, the robot discovered shortcuts and found ways to cheat, which the researchers had to intervene and instruct the robot not to do. The project lead researchers, Thomas Bi and Prof. Raffaello D'Andrea, plan to open-source the project on a website, enabling anyone to participate in cutting-edge AI research.

Related reads

Popular posts from this blog

Apple's Next Gen iPad Lineup: M3 MacBook Air and Refined iPad Pros on the Way?

Intel Unveils Arrow Lake Gaming CPUs with AI Accelerators, Lunar Lake Brings Huge IPC Uplifts

MediaTek Optimizes Chips for Next-Gen Gemini Nano Devices