I wonder if improving Minic's handcrafted evaluation function would improve the evaluation quality of Minic scored data.xr_a_y wrote: ↑Fri Dec 25, 2020 6:08 pm I think many things are involved here, probably too much ! :
- data quality : I tried many different things (from games, from random play, from inside search tree), from depth 5 to 16, from 200M to 2B pack, only quiet position, only non capture next move, ...
- evaluation quality : clearly SF scored data looks better than Minic ones so probably RL might be a good idea !
- NNUE speed : for now the Seer style evaluation is twice as slow as the current SF one, partly because of float32 being used instead of int16. So a lot to be gained from quantization probably.
Minic version 3
Moderators: hgm, Rebel, chrisw
-
- Posts: 512
- Joined: Tue Sep 29, 2020 4:29 pm
- Location: Dublin, Ireland
- Full name: Madeleine Birchfield
Re: Minic version 3
-
- Posts: 319
- Joined: Sat Oct 31, 2020 1:04 am
- Full name: Aleksey Glebov
Re: Minic version 3
Hi, Vivien!
Nice to see you'r developing your own nets.
What is "5 minic_3.02"? Does it use HCE?
I am going to include some Minic versions to my nearest tournaments.
Happy New Year! Aleksey.
Nice to see you'r developing your own nets.
What is "5 minic_3.02"? Does it use HCE?
I am going to include some Minic versions to my nearest tournaments.
Happy New Year! Aleksey.
Incredibly fast systems miscount incredibly fast.
-
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Minic version 3
Hi, yes this is HCE. I will continue to develop HCE because I like that and this is used for the Minic skills and features parameters.
-
- Posts: 319
- Joined: Sat Oct 31, 2020 1:04 am
- Full name: Aleksey Glebov
Re: Minic version 3
How many changes in 3.02 HCE compared to 2.53 HCE?
Incredibly fast systems miscount incredibly fast.
-
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Minic version 3
Almost none . Just some fixes and options.
-
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Minic version 3
Minic 3.03 is release.
No strength increase for HCE again, but some code cleanup and little fixes (maybe the endgame issue viewed in some tourney where Minic cannot mate in won position).
This release is also associated with a new net : "niggling nymph" that was built on FRC data and is thus stronger than previous nets in FRC situations (https://github.com/tryingsomestuff/NNUE-Nets).
Short TC tests for standard chess
Short TC tests for FRC
I'm now working on :
- HCE texel tuning using pure Minic data
- deep depth NNUE training (depth 16)
- NNUE quantization
Have fun
No strength increase for HCE again, but some code cleanup and little fixes (maybe the endgame issue viewed in some tourney where Minic cannot mate in won position).
This release is also associated with a new net : "niggling nymph" that was built on FRC data and is thus stronger than previous nets in FRC situations (https://github.com/tryingsomestuff/NNUE-Nets).
Short TC tests for standard chess
Code: Select all
Rank Name Elo +/- Games Score Draw
1 minic_2.53_napping_nexus 245 18 1251 80.4% 29.3%
2 minic_2.53_nascent_nutrient 151 17 1251 70.4% 31.7%
3 minic_3.02_nettling_nemesis 80 16 1251 61.4% 32.4%
4 minic_dev_niggling_nymph -58 16 1251 41.7% 35.2% ****
5 minic_3.02_narcotized_nightshift -70 16 1251 40.0% 33.6%
6 minic_3.02 -86 16 1251 37.9% 30.0%
7 minic_dev -98 16 1251 36.3% 31.3%
8 minic_3.01_nefarious_nucleus -132 17 1251 31.9% 28.4%
Code: Select all
Rank Name Elo +/- Games Score Draw
1 minic_2.53_napping_nexus 290 16 2272 84.1% 16.9%
2 minic_2.53_nascent_nutrient 203 14 2271 76.3% 19.0%
3 minic_3.02_nettling_nemesis -30 13 2271 45.7% 20.7%
4 minic_3.02 -30 13 2271 45.6% 22.9%
5 minic_dev -44 13 2271 43.7% 22.5%
6 minic_dev_niggling_nymph -53 13 2271 42.4% 22.1% ****
7 minic_3.02_narcotized_nightshift -79 13 2271 38.8% 23.2%
8 minic_3.01_nefarious_nucleus -206 15 2272 23.4% 15.5%
- HCE texel tuning using pure Minic data
- deep depth NNUE training (depth 16)
- NNUE quantization
Have fun
-
- Posts: 319
- Joined: Sat Oct 31, 2020 1:04 am
- Full name: Aleksey Glebov
Re: Minic version 3
Hi, Vivien!
Thanks for the new version! It's strange for me that in your tests 3.0.1 NeNu is much weaker than 3.0.2 NaNi. In my tournament it plays even stronger.
Thanks for the new version! It's strange for me that in your tests 3.0.1 NeNu is much weaker than 3.0.2 NaNi. In my tournament it plays even stronger.
Incredibly fast systems miscount incredibly fast.
-
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Minic version 3
Maybe it depends on the opponent set (and of course the number of games). Also my tests are fast TC at 10s+0.1
-
- Posts: 319
- Joined: Sat Oct 31, 2020 1:04 am
- Full name: Aleksey Glebov
Re: Minic version 3
Anyways, both versions play very interesting positional chess (though with some oddities from 3.0.2 NaNi such as unreasonably high evals or lack of underpromotion knowledge etc.).
Incredibly fast systems miscount incredibly fast.
-
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Minic version 3
I just had the opportunity to test Minic3 on a AMD Ryzen Threadripper 3990X ... 55Mnps for 128 threads, quite cool