Komodo 14.1 Release and Dragon Announcement

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Dann Corbit, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
carldaman
Posts: 2094
Joined: Sat Jun 02, 2012 12:13 am

Re: Komodo 14.1 Release and Dragon Announcement

Post by carldaman » Tue Nov 03, 2020 7:24 am

lkaufman wrote:
Tue Nov 03, 2020 4:36 am
jmartus wrote:
Mon Nov 02, 2020 5:55 pm
How is the playing style of your nnue implementation?
Well, it's hard to make general statements about playing style. I would say it is more human-like, even though it was trained on engine games, because it is less reliant on arbitrary rules that might not be appropriate for a given position. With very short searches the difference is obvious, but as searches become deeper the differences become smaller.
A better question would be: does K-Dragon retain the style of the old Komodo?

Werewolf
Posts: 1349
Joined: Thu Sep 18, 2008 8:24 pm

Re: Komodo 14.1 Release and Dragon Announcement

Post by Werewolf » Tue Nov 03, 2020 7:59 am

lkaufman wrote:
Mon Nov 02, 2020 5:08 pm
Komodo 14.1 Release and Dragon Announcement

The improvement from Komodo 14.1 to Dragon is enormous, even larger than the gain Stockfish got from
this NNUE idea.
Strange.
For ages the marketing line / general understanding is that SF has the better search, and Komodo the better EF.

Madeleine Birchfield
Posts: 312
Joined: Tue Sep 29, 2020 2:29 pm
Location: Dublin, Ireland
Full name: Madeleine Birchfield

Re: Komodo 14.1 Release and Dragon Announcement

Post by Madeleine Birchfield » Tue Nov 03, 2020 8:23 am

Werewolf wrote:
Tue Nov 03, 2020 7:59 am
Strange.
For ages the marketing line / general understanding is that SF has the better search, and Komodo the better EF.
That changed when Stockfish adopted neural networks for its evaluation function earlier this year. Then all of a sudden Stockfish had a much superior evaluation function over Komodo and still its much better search. However, Stockfish's own neural network is extremely unoptimised, so there is still a possibility that if Komodo Dragon trained its neural network well enough it would be able to surpass Stockfish with a better evaluation function again.

Andrew
Posts: 178
Joined: Wed Mar 08, 2006 11:51 pm
Location: Australia

Re: Komodo 14.1 Release and Dragon Announcement

Post by Andrew » Tue Nov 03, 2020 8:43 am

I'd love to see these engines train networks specifically for KP and KPR endings. They are the most common in normal play.

However the big question is how big they would need to be useful. 1Mb? 10 Mb?

ELO advantage, tiny or reasonable?

Maybe useful studying certain middle or endgame positions/studies?

Lots of questions, but I hope we see experiments to get some answers!

Andrew

Madeleine Birchfield
Posts: 312
Joined: Tue Sep 29, 2020 2:29 pm
Location: Dublin, Ireland
Full name: Madeleine Birchfield

Re: Komodo 14.1 Release and Dragon Announcement

Post by Madeleine Birchfield » Tue Nov 03, 2020 9:00 am

Andrew wrote:
Tue Nov 03, 2020 8:43 am
I'd love to see these engines train networks specifically for KP and KPR endings. They are the most common in normal play.

However the big question is how big they would need to be useful. 1Mb? 10 Mb?

ELO advantage, tiny or reasonable?

Maybe useful studying certain middle or endgame positions/studies?

Lots of questions, but I hope we see experiments to get some answers!

Andrew
I think Andrew Grant's Ethereal and Jonathan Kreuzer's SlowChess both use networks for king and pawn endgames and other endgames, with a moderate amount of elo gain. Most other engines are moving towards using a neural network for the entire evaluation function, entirely sidestepping the need for specialised networks for endgames.

Raphexon
Posts: 380
Joined: Sun Mar 17, 2019 11:00 am
Full name: Henk Drost

Re: Komodo 14.1 Release and Dragon Announcement

Post by Raphexon » Tue Nov 03, 2020 9:07 am

Werewolf wrote:
Tue Nov 03, 2020 7:59 am
lkaufman wrote:
Mon Nov 02, 2020 5:08 pm
Komodo 14.1 Release and Dragon Announcement

The improvement from Komodo 14.1 to Dragon is enormous, even larger than the gain Stockfish got from
this NNUE idea.
Strange.
For ages the marketing line / general understanding is that SF has the better search, and Komodo the better EF.
Don't believe marketing.
I don't think anyone has comprehensive proof of Komodo's eval having been better in the past x years.

There used to be "Komodo scaling" on multicores when they were among the first to use LazySMP and the rest were still using YBWC, but those days are long gone.

marsell
Posts: 68
Joined: Tue Feb 07, 2012 10:14 am

Re: Komodo 14.1 Release and Dragon Announcement

Post by marsell » Tue Nov 03, 2020 9:20 am

dkappe wrote:
Mon Nov 02, 2020 7:45 pm

This “blandness blender” theory isn’t supported by any evidence.
+1

Marcus9
Posts: 56
Joined: Mon May 13, 2019 4:05 pm
Full name: Marco Giorgio

Re: Komodo 14.1 Release and Dragon Announcement

Post by Marcus9 » Tue Nov 03, 2020 9:30 am

Thanks for freeing the Dragon!
Are there any Dragon vs. Human matches scheduled?
I find them so exciting

User avatar
Thomas Lagershausen
Posts: 292
Joined: Mon Jun 11, 2007 4:59 pm

Re: Komodo 14.1 Release and Dragon Announcement

Post by Thomas Lagershausen » Tue Nov 03, 2020 10:09 am

Sorry to say, but where is the data?

Till now Komodo Dragon is a papertiger. :!:
TL

User avatar
Ozymandias
Posts: 1323
Joined: Sun Oct 25, 2009 12:30 am

Re: Komodo 14.1 Release and Dragon Announcement

Post by Ozymandias » Tue Nov 03, 2020 10:36 am

Thomas Lagershausen wrote:
Tue Nov 03, 2020 10:09 am
Sorry to say, but where is the data?

Till now Komodo Dragon is a papertiger. :!:
After 54 games at CCC, it's only one and a half point behind SF @ 10+5. I imagine the final version will be on par.

Post Reply