Re:AlphaGo shows its true strength in 3rd victory against Le...
by lambda on Saturday March 12, 2016 @05:18PM
(#11274895)
They mentioned what the training input to AlphaGo was in the paper; a database of a few hundred thousand games from dan ranked players on KGS. This means mostly amateur players, though there are a few professionals who play on KGS as well.
However, this only gets you so far, and the training set is fairly small compared to what you want to really train both the policy and value networks well. So then they had it play millions of games against different versions of itself, training both a new policy network and the value network based on that.
It's unlikely that Lee Sedol's games made much if any impact on AlphaGo's training. It was bootstrapped off of high-level amateur, and some casual pro, play, but from then on it just trained against itself.
Re:AlphaGo shows its true strength in 3rd victory against Le...
by sdenton4 on Saturday March 12, 2016 @03:30PM
(#11274397)
Well, I'm not even sure if they attached individual identities to the games fed in as features...
Re:AlphaGo shows its true strength in 3rd victory against Le...
by arcticfox on Saturday March 12, 2016 @04:09PM
(#11274564)
The implication is that because Sedol wins more tournaments than almost anyone else, if you feed "Tournament winner" or "ELO" etc. as a feature, his games will be much more weighted than others.
So even if AlphaGo isn't explicitly designed to play against his style, it's implicitly trained in it.
But it's pretty subtle and I'm guessing that the volume of high-level tournaments overwhelms any effect, as the AlphaGo team said.
I don't know the details of the algorithm and perhaps it doesn't give more explicit weight to his games. But I wouldn't be surprised if after some iterations the algorithm decided to give more implicit weight to the games of the world leaders.