ETH Zurich Creates Deep Reinforcement Learning Based Robot that Plays Labyrinth Marble Game
ETH Zurich Creates Deep Reinforcement Learning Based Robot that Plays Labyrinth Marble Game
ETH Zurich Creates Deep Reinforcement Learning Based Robot that Plays Labyrinth Marble Game
By ETH Zurich
December 19, 2023
Summary
An AI technique known as deep reinforcement learning has pushed back the limits of what can be achieved with autonomous systems and AI, achieving superhuman performance in a variety of different games such as chess and Go, video games and navigating virtual mazes.
Researchers at ETH Zurich have created an AI robot named CyberRunner whose task is to learn how to play the popular and widely accessible labyrinth marble game.
The labyrinth is a game of physical skill whose goal is to steer a marble from a given start point to the end point.
CyberRunner applies recent advances in model-based deep reinforcement learning to the physical world and exploits its ability to make informed decisions about potentially successful behaviors by planning real-world decisions and actions into the future.
Using this memory, the model-based deep reinforcement learning algorithm learns how the system behaves, and based on its understanding of the game it recognizes which strategies and behaviors are more promising.
Importantly, the robot does not stop playing to learn; the algorithm runs concurrently with the robot playing the game.
The AI robot outperforms the previously fastest recorded time, achieved by an extremely skilled human player, by over 6%. Interestingly, during the learning process, CyberRunner naturally discovered shortcuts.
Reference
ETH Zurich. (2023, December 19). ETH Zurich creates deep reinforcement learning based robot that plays Labyrinth Marble Game. StartupHub.ai. https://www.startuphub.ai/eth-zurich-creates-deep-reinforcement-learning-based-robot-that-plays-labyrinth-marble-game/