Maluuba researcher Harm van Seijen, who also authored a paper (opens in a new tab) on the AI research (which is being submitted to Cornell University on Wednesday), told me that they designed their AI based on how the iPhone is made. Pac-Man and reached a maximum score of 999,999, which, according to Microsoft (opens in a new tab), no AI or human has ever achieved before. Using this method, the AI algorithm soon mastered Ms. In other words, tasks like avoiding ghosts (which kill on touch in the game) were prioritized over other tasks. Individual agents had their own reward functions and the manager would prioritize tasks that were more important.
The manager agent would then analyze how the agents approached each task and the intensity they applied to them to decide which paths were, in fact, the best.
Pac-Man game pellets, while others were told to avoid ghosts at all costs. Those agents broke the game down into tasks and sub-tasks and were rewarded (or reinforced) for pursuing those tasks.įor example, some agents were charged with finding specific Ms. Researchers with deep learning company Maluuba, which Microsoft acquired earlier this year, decided to tackle the deceptively simple arcade game after developing an unusual AI algorithm that uses a team of intelligent agents overseen by a manager agent to play Ms. But now it's been laid low - like chess (opens in a new tab), Go, and poker before it - by artificial intelligence. Pac-Man was supposed to be the more difficult arcade game.
0 kommentar(er)
