search

PraxTube / chess-ai

A chess AI that uses alpha-beta to find the best move
MIT License
0 stars 1 forks source link

AI: Let AI play against itself at different depths (1 vs 2, 2 vs 3, etc.) #36

Closed PraxTube closed 1 year ago

PraxTube commented 1 year ago

I think it would be pretty fun to see the AI play against itself at different depths. This should show that our AI becomes smarter with each depth.

PraxTube commented 1 year ago

@joris68 I marked you because I think this would be pretty useful for debugging purposes and it also shouldn't be too hard to implement. I think the best way to realize this feature, is by creating a new file and then calling the main function (or the play.py script) from there.

PraxTube commented 1 year ago

I played around with this a bit (with depth 3 vs 4) and it seemed somewhat okay. I thought it would play significantly better but it was only slightly better. Though I didn't test this too much either.

One problem still persisted: Stalemate, endless loop. The AI's just repeat the same move over and over. This should be fixed through #49.

PraxTube commented 1 year ago

Closing this because it's a waste of time (for now).