[email protected] wrote on 06/20/2011 03:35:21 PM:
> I took a brief look at the Segal paper and it seems well written to me.
Thanks. :-)
> You implied that the scalability stops far short of perfect play but
> I don't see any such claim in the paper. In fact, the 4,150 ELO
> projection in the paper seems (if anything) too high. At 100 ELO
> per rank, this represents about 53 ranks of improvement over a 1
> minute per game fuego player (which at 1 minute is still far better
> than the very weakest kyu beginners.)
> When I talk about scalability it is a given that it declines as you
> approach perfect play and the curve flattens out, so the papers
> conclusion about the "limits of scaling" in no way refutes (nor
> proves) the idea that scaling suddenly stops well short of perfect
> play. In fact it seems to indicate to me that perfect play may be
> farther away than we think and that computers have a good handle on it.
I agree that the paper does not do enough to explain why I think Fuego's
asymptote is below that of optimal play. I just sent a note with some
extra details that explains this further. But basically, the projection
in the paper puts our our 32 core / 112 thread competition machine
at roughly 3700 elo for a 15 minute time control, and roughly 3800 for a
30 minute time control. I estimate the latest versions of Erica and Zen
and are 300 elo stronger than Fuego when both are run on competition
hardware.
That places these programs at 4,100 elo on this scale. There is no way
these
programs are within 50 elo of top experts let alone perfect play :-).
- Rich
_______________________________________________
Computer-go mailing list
[email protected]
http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
