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

Bots are superhuman in self-play Hanabi: https://ai.facebook.com/blog/building-ai-that-can-master-com...

The remaining challenge is getting it to play well with human partners. Doing that requires modeling human conventions rather than learning weird bot conventions. That's hard because while you can collect essentially unlimited data through self play, it's hard to collect a lot of data playing with humans using reinforcement learning. AI algorithms are really bad at sample efficiency.




Consider applying for YC's W25 batch! Applications are open till Nov 12.

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

Search: