News for hackers. Stuff that matters.

A comment on Mastering Chess and Shogi by Self-Play with General Reinforcement Learning. Parent comment

Re:Mastering Chess and Shogi by Self-Play with General Reinf... by deepnotderp on Wednesday December 06, 2017 @12:23AM (#15858746)
Right right, but my comparison was between giraffe and AlphaGo , not neural networks and Stockfish.
[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by joshuamorton on Wednesday December 06, 2017 @01:44AM (#15859085)
But it looks like AlphaGo is searching fewer positions per second than Giraffe did.

AlphaZero evaluates 80K positions per second, according to this paper, and the Giraffe paper says that Giraffe averaged 258570 evaluations per second when running STS.

While we can't directly compare the computer power, this implies that AZ has learned a better representation.

[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by allenz on Wednesday December 06, 2017 @06:38PM (#15866177)
It's unclear how much of the "better representation" was due to better algorithm vs. more compute/deeper NN.
[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by joshuamorton on Wednesday December 06, 2017 @10:33PM (#15867428)
Giraffe was trained until convergence. Maybe if there was more compute power then, a different model would have been used, but that's deep into the world of silly hypotheticals.
[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by Retric on Wednesday December 06, 2017 @08:39AM (#15860944)
By starving the competitor of computing power, if you compare A and B you can't give A 10+x the compute power and assume a fair comparison. What's interesting is a demonstration that enough compute power let's NN reach beyond human level play. Though, I don't think that was ever really in doubt.
[ Parent | on HN ]