Hacker News Reader

Interesting way of approaching the problem.

I didn't realize the go solution "just" used monte carlo branching. Still impressive, but does not seem as revolutionary as it's been portrayed.

View on HN

The insight was to use CNNs to prune the search space. In a sense, the AlphaGo algorithm is to MCTS as importance sampling is to regular Monte Carlo. However, even without the search part, AlphaGo crushes MCTS-based Go algorithms (see https://www.tastehit.com/blog/google-deepmind-alphago-how-it...). That in and of itself is quite extraordinary.

Reply on news.ycombinator.com