Google Deepmind DQN plays Atari Breakout
17.2 هزار بار بازدید -
8 سال پیش
-
Google Deepminds deep learning algorithm
Google Deepminds deep learning algorithm DQN learns to play Atari Breakout. It made some visible progress and even found out, that it is most effective to dig a tunnel and let the ball run behind the wall.
The algorithm knew nothing about the controls. It was fed with raw pixel data and had to decide on the next action. It had no idea of the principle of a ball and the game itself. The only goal was to maximize the score.
The algorithm knew nothing about the controls. It was fed with raw pixel data and had to decide on the next action. It had no idea of the principle of a ball and the game itself. The only goal was to maximize the score.
8 سال پیش
در تاریخ 1395/08/01 منتشر شده
است.
17,266
بـار بازدید شده