Thread

1. janalsncm · 1790977486 · focus · HN ↗

   > The algorithm also learned far faster—it played about 34 times fewer games than DeepNash, and still ended up much stronger.

   Imo, this is the critical piece and what makes the AI work at all.

   With hidden information games, the best move depends on information you don’t have. So a move could be good or bad, it just depends on something that’s impossible to know.

   You’d like to search ahead, meaning “if I do this they will do that” but that’s impossible since you don’t even know what the opponent can do because you don’t know their hidden state.

   If the possible hidden states are randomly distributed, you are screwed. It’s just like rock paper scissors: there’s no best move if your opponent is unpredictable.

   However if you can quickly learn to predict their moves, it becomes possible to make informed decisions about what to do.

   1. williamtell · 1790983167 · focus · HN ↗

      It would be easy enough for a player to be purely random if that was all it took. I think the tension is that piece rank makes some layouts and move strategies more equal than others and calculating the best ones for what has been uncovered so far makes the best layouts not the best layouts.

Unofficial Hacker News client; not affiliated with Y Combinator.