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 arcticfox on Wednesday December 06, 2017 @08:15AM (#15860815)
Can't those teraflops be applied to evaluating more positions instead of deciding which positions to evaluate?

It seems that the metric should be compute time, not positions evaluated.

[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by nl on Wednesday December 06, 2017 @09:30AM (#15861243)
Presumably they both had equal clock time - that is a standard chess rule so it would be surprising to see it different.
[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by setr on Wednesday December 06, 2017 @10:20AM (#15861667)
Wall clock != cpu clock

I can do more in the same wall time with a faster cpu(s); I can afford inefficiencies that the opponent cannot, and accomplish just as much.

[ Parent | on HN ]