And yes, MCTS worked well for Go, but notice how the combination boosted it to new levels? And deep nets without MCTS also worked very well on Go, outperforming MCTS only approaches (by FAIR and was the top before being dethroned by AlphaGo).
And yes, MCTS worked well for Go, but notice how the combination boosted it to new levels? And deep nets without MCTS also worked very well on Go, outperforming MCTS only approaches (by FAIR and was the top before being dethroned by AlphaGo).
> This is a fallacy, AlphaGo didn't increase very much with additional hardware at all
It did. Please take a look at the page 36 of the original paper. (https://gogameguru.com/i/2016/03/deepmind-mastering-go.pdf) The performance did not grow linearly, but the increases were vert significant.
>it's elo would still have been higher than lee se-dol's elo
I seriously doubt it would win that match. One-GPU version lost to 8-GPU version around 95% of all games.
The paper is somewhat misleading in estimating relative performance of AlphaGo compared to older programs, because (as far as I know) while all of them were run on the same hardware, only AlphaGo used GPU acceleration.