AIs ability to beat human players in games like chess and GO is no longer surprising.
But physical skill has remained a human prerogative until now.
But if youve ever played it, you know its actually quite challenging.
40% off TNW Conference!
While playing the game, CyberRunner makes observations of the labyrinth and receives rewards based on its performance.
It keeps a memory of the collected experience, which thealgorithmuses to learn how the system behaves.
Based on this knowledge, its able to recognise the most promising behaviours.
The robot received 6.06 hours of practice.
CyberRunner completed the game in 14.48 seconds faster by over 6% compared to the human record holder.
We believe that this is the ideal testbed for research in real-world machine learning and AI.
Prior to CyberRunner, only organisations with large budgets and custom-made experimental infrastructure could perform research in this area.
Now, for less than 200 dollars, anyone can engage in cutting-edge AI research, said DAndrea.
The ultimate in Citizen Science!
With a background in the humanities, she has a soft spot for social impact-enabling technologies.
