Video 2: Demonstration of Learning Progress in the Game Breakout

FromHuman-level control through deep reinforcement learning

Journal name:
Nature
Volume:
518,
Pages:
529–533
Date published:
DOI:
doi:10.1038/nature14236
Streaming video does not reproduce the original video quality. Download the video using the link below to view at original quality.
This video shows the improvement in the performance of DQN over training (i.e. after 100, 200, 400 and 600 episodes). After 600 episodes DQN finds and exploits the optimal strategy in this game, which is to make a tunnel around the side, and then allow the ball to hit blocks by bouncing behind the wall. Note: the score is displayed at the top left of the screen (maximum for clearing one screen is 448 points), number of lives remaining is shown in the middle (starting with 5 lives), and the “1” on the top right indicates this is a 1-player game.

Additional data