日本語Windows® 7/8/8.1/10 (32/64bit)
That'd be nice.I hope there will be an iOS version as well.
Very roughly speaking, is it fair to say it's at least 1-stone better than the previous version ?a win rate of 95% against the previous version.
Probably more.EdLee wrote:1-stone better than the previous version ?
( Curious about its winrate giving 2 stones to the previous version. )
The self play trap?Elom wrote:Denniss Hassabis said Alphago performs better against weaker versions of itself than it does against weaker humans. It's likely the same for all AI.
Well, with self play, that's what it is trained to do. Perhaps diminishing returns kick in, in terms of points. That is, even with the same win rate difference, the wins get smaller and smaller. But against other players with different strengths and vulnerabilities, at some point those small refinements do not produce the same win rate differences.hyperpape wrote:I imagine that this could be true of people, if we could freeze someone's play and have them play against themselves. A significant part of what you learn is identifying your own bad patterns. It just might be the case that AI is more predictable (and learns primarily through self-play) so it is even better at exploiting its past selves' weaknesses.
Bill Spight wrote:
The self play trap?
There may be some human exampleshyperpape wrote:I imagine that this could be true of people, if we could freeze someone's play and have them play against themselves. A significant part of what you learn is identifying your own bad patterns. It just might be the case that AI is more predictable (and learns primarily through self-play) so it is even better at exploiting its past selves' weaknesses.
.
.