News for hackers. Stuff that matters.
Re:'World Models,' an old idea in AI, mount a comeback by deepsquirrelnet on Tuesday September 02, 2025 @06:59PM (#45110225)
> I’ve tried throwing masses of game state data at latest models in pytorch. Unusable. It Makes really dumb moves. In fact one big issue is that it often suggests invalid moves and the best way to avoid this is to implement the board game logic in full to validate it.

It sounds like you need RL. You could try setting up some reward functions with evaluators. I’m not sure what your architecture is, but something to try.

There are no comments on this comment yet.