Hacker News new | past | comments | ask | show | jobs | submit login

The goal isn't to beat mario as efficiently as possible, but to create a program that can learn to play literally any game.

Also what is that AI doing when it decides to jump into the pit at 0:45? It clearly sees the path to jump over it, but it chooses the one that jumps into it. Watching it frame by frame it seems to figure out a path to jump out of the pit several times, but chooses not to, until eventually it finally does.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: