ai plays super mario bros for 5 minutes straight
HTML-код
- Опубликовано: 14 окт 2024
- i am in a writers block at the moment so no music video for now
i present another one of my hobbies (AI if it isn't obvious)
this is a reinforcement learning network using the A2C (Advantage Actor-Critic) algorithm to play 1-1 in super mario bros
in the video the episodes presented are around episodes 60-90 in training
the ai receives positive reward for any actions that involve getting to the end of the level (moving right and squashing enemies) and receives a consequence for actions that don't involve getting to the goal (being alive, moving left, and dying)
layman's terms:
be good at the game = 👏 🎉
be bad at the game = ❌ 👎
Bro forgot to hold the button
yes even at episode 1080 it still does not jump the pipes first try (but gets unstuck quicker or jumps between pipes entirely)
parts where it freezes are where both agent and critic are evaluated for loss
😭😭 do you have a platform where we can be friends? I need more composer buddies
youtube will have to do for now until i set up a discord server i'll check once every 5 years