Learning to play Super Mario Bros
Here is a video of a project from my lecture “Applied Neuroinformatics” which I tought at University of Applied Sciences Ravensburg-Weingarten. It shows how Mario learns to improve its behavior by reinforced sensorimotor interactions. A paper describing our technique is currently under review.
Thanks to the developers of Mario AI for sharing their source code!!!
Video Bookmarks
- 0:00 Start learning using action filters 1+2
- 2:29 Learning progress / behaviour after 500 episodes
- 4:29 After 990 episodes (the hopping is gone)
- 5:18 Using a stronger action filter (1-4) and more enemies
- 6:22 Patterns are forming
- 7:18 Successful runs after 20 episodes