Hacker News new | ask | show | jobs
by noambrown 1620 days ago
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.