[Computer-go] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
sheppardco at aol.com
Thu Dec 7 07:54:45 PST 2017
> Which is IMHO missing the point a bit ;-)
I saw it the same way, while conceding that the facts are accurate.
It makes sense for SF to internalize the details before making decisions. At some point there will be a realization that AZ is a fundamental change.
>What about the data point that AlphaGo Zero gained 2100 Elo from its tree search? In a game commonly considered less tactical?
That is a common perception, especially among those who have never debugged a Go program. :-)
I was coming at it from the other direction, reasoning that since SF and AZ are close to perfect at chess, then there is less to gain from speed. (Whereas I doubt that AGZ is close to perfect at Go.)
All of this is subject to my money back guarantee: my opinions are guaranteed wrong, or your money back. :-)
From: Computer-go [mailto:computer-go-bounces at computer-go.org] On Behalf Of Gian-Carlo Pascutto
Sent: Thursday, December 7, 2017 8:17 AM
To: computer-go at computer-go.org
Subject: Re: [Computer-go] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
On 7/12/2017 13:20, Brian Sheppard via Computer-go wrote:
> The conversation on Stockfish's mailing list focused on how the match
> was imbalanced.
Which is IMHO missing the point a bit ;-)
> My concern about many of these points of comparison is that they
> presume how AZ scales. In the absence of data, I would guess that AZ
> gains much less from hardware than SF. I am basing this guess on two
> known facts. First is that AZ did not lose a game, so the upper bound
> on its strength is perfection. Second, AZ is a knowledge intensive
> program, so it is counting on judgement to a larger degree.
What about the data point that AlphaGo Zero gained 2100 Elo from its tree search? In a game commonly considered less tactical?
Computer-go mailing list
Computer-go at computer-go.org
More information about the Computer-go