Search found 259 matches

by dkappe
Thu Sep 05, 2019 3:01 am
Forum: Computer Chess Club: General Topics
Topic: Bad Gyal Data now available
Replies: 1
Views: 420

Bad Gyal Data now available

I've started to upload the 25GB of Bad Gyal data. Here a brief description and a link to the files.

https://github.com/dkappe/leela-chess-w ... -Gyal-Data

Please let me know if you do something interesting with the data or if you have any issues.
by dkappe
Tue Sep 03, 2019 7:36 pm
Forum: Computer Chess Club: General Topics
Topic: SIMEX 2.1
Replies: 26
Views: 3201

Re: SIMEX 2.1

Looking at Good Gyal 7, which is a supervised learning net trained on lichess and stockfish data, and testing it against a collection of diverse leela nets, it’s about a 55%-60% similarity score against most other nets. That’s fairly low out of the group — seeing values over 60% is not uncommon. Com...
by dkappe
Tue Sep 03, 2019 12:13 pm
Forum: Computer Chess Club: General Topics
Topic: SIMEX 2.1
Replies: 26
Views: 3201

Re: SIMEX 2.1

Someone over at the lczero discord ran this on a variety of nets, including some supervised learning ones. Overall they seemed to have much higher similarity than ab engines.
by dkappe
Mon Sep 02, 2019 6:02 pm
Forum: Computer Chess Club: General Topics
Topic: How much time handicap can LCzero give Magnus Carlsen ?
Replies: 12
Views: 2127

Re: How much time handicap can LCzero give Magnus Carlsen ?

I’d hazard a guess that even Mean Girl (32x4 net) running on CPU could handle Magnus.
by dkappe
Thu Aug 29, 2019 6:12 pm
Forum: Computer Chess Club: General Topics
Topic: DQ 1.2 vs Bad Gyal 7 - the power of policy
Replies: 7
Views: 1194

Re: DQ 1.2 vs Bad Gyal 7 - the power of policy

If I want to win a correspondence game, I’ll reach for the strongest T40 net. When I want to prepare for OTB against human opposition, I reach for Bad Gyal. It suggests moves and lines that are not always objectively best, but in practice best against human opponents. Plus they tend to be plans I ca...
by dkappe
Thu Aug 29, 2019 4:35 pm
Forum: Computer Chess Club: General Topics
Topic: DQ 1.2 vs Bad Gyal 7 - the power of policy
Replies: 7
Views: 1194

DQ 1.2 vs Bad Gyal 7 - the power of policy

Two nets that, as far as I know, use similar source material. DarkQueen uses lichess games that have been annotated by Stockfish. Bad Gyal 7 uses lichess games annotated with q and policy from Stockfish. The main difference seems to be policy. So far it's a walkover by the smaller Bad Gyal 7. Here a...
by dkappe
Mon Aug 26, 2019 5:20 pm
Forum: Computer Chess Club: General Topics
Topic: Match between SF 10 and Fat Fritz
Replies: 6
Views: 1043

Re: Match between SF 10 and Fat Fritz

So, Chessbase marketing of Fat Fritz started in full. The regular Lc0 branch of T499xx nets does use 100 most popular human 4-plier openings, and if one is curious about KID specifics, main variations of it could have been added as openings. I am not sure Fat Fritz plays KID any better than 499xx n...
by dkappe
Mon Aug 26, 2019 4:41 pm
Forum: Computer Chess Club: General Topics
Topic: CCRL Benchmark Net
Replies: 3
Views: 775

Re: CCRL Benchmark Net

dkappe wrote:
Mon Aug 26, 2019 5:06 am

It looks to be about 200 elo weaker than Bad Gyal 7, which is surprising to me.
Make that 250 elo. I think that this is a good piece of evidence that the SL tools surrounding lc0 yield suboptimal results.
by dkappe
Mon Aug 26, 2019 3:01 pm
Forum: Computer Chess Club: General Topics
Topic: CCRL Benchmark Net
Replies: 3
Views: 775

Re: CCRL Benchmark Net

The architecture is different, but other than that, no idea.