Hacker News new | ask | show | jobs
by whitegrape 3739 days ago
More like anything with a guided search algorithm will be said to be like AlphaGo. In general I think the field may be warming up to the idea that "whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought."[1] MCTS does exceptionally well at Go all by itself. When coupled with something (in this case trained neural nets) that can give it better-than-random guidance in exploring the state space, it's no surprise it does even better.

[1] http://lesswrong.com/lw/vq/the_weighted_majority_algorithm/
1 comments
gcp 3738 days ago
MCTS does exceptionally well at Go all by itself. When coupled with something (in this case trained neural nets) that can give it better-than-random guidance in exploring the state space, it's no surprise it does even better.

The tricky part is that using the "best (rather than better) than random guidance" in the Monte Carlo simulations makes the performance worse.

We don't understand very deeply why that is.

link