Do you have plans to support FRC?
Introducing Igel chess engine
Moderators: hgm, Rebel, chrisw
-
- Posts: 1142
- Joined: Thu Dec 28, 2017 4:06 pm
- Location: Argentina
Re: Introducing Igel chess engine
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls
-
- Posts: 288
- Joined: Sat Jun 30, 2018 10:58 pm
- Location: Ukraine
- Full name: Volodymyr Shcherbyna
Re: Igel 3.1.0
Igel 3.1.0 at https://github.com/vshcherbyna/igel/releases/tag/3.1.0 (official executable binaries for Windows and IGN net).
This release brings adequate improvement in strength.
What's new:
- Scale eval at 1280
- More aggressive pruning of quiets when not improving
- Use 150 cp when razoring
- Avoid tt cutoff for rule50
- Improve statistics in SMP mode
- New network trained using 16B of d5-d8 data from Igel HCE/ign-1-139b702b with d16 validation using ign-1-139b702b
Regression run against Igel 3.0.5:
Long Time Control With Increment
Code: Select all
ELO | 30.13 +- 2.64 (95%)
CONF | 60.0+0.60s Threads=1 Hash=64MB
GAMES | N: 20000 W: 3906 L: 2176 D: 13918
-
- Posts: 1362
- Joined: Sat Jul 21, 2018 7:43 am
- Location: Szentendre, Hungary
- Full name: Gabor Szots
Re: Introducing Igel chess engine
Excellent news Volodymyr.
Note: I had to edit the makefile because it points to a previous net file.
Note: I had to edit the makefile because it points to a previous net file.
Gabor Szots
CCRL testing group
CCRL testing group
-
- Posts: 288
- Joined: Sat Jun 30, 2018 10:58 pm
- Location: Ukraine
- Full name: Volodymyr Shcherbyna
Re: Introducing Igel chess engine
Thank you Gabor.
I removed the old network reference.
I removed the old network reference.
-
- Posts: 1495
- Joined: Sat Feb 06, 2021 8:06 am
- Full name: Alex Morales
Re: Igel 3.1.0
Thank you Voffka and welcome back!voffka wrote: ↑Fri Jun 03, 2022 1:00 pm
Igel 3.1.0 at https://github.com/vshcherbyna/igel/releases/tag/3.1.0 (official executable binaries for Windows and IGN net).
This release brings adequate improvement in strength.
What's new:
- Scale eval at 1280
- More aggressive pruning of quiets when not improving
- Use 150 cp when razoring
- Avoid tt cutoff for rule50
- Improve statistics in SMP mode
- New network trained using 16B of d5-d8 data from Igel HCE/ign-1-139b702b with d16 validation using ign-1-139b702b
Regression run against Igel 3.0.5:
Long Time Control With Increment
Code: Select all
ELO | 30.13 +- 2.64 (95%) CONF | 60.0+0.60s Threads=1 Hash=64MB GAMES | N: 20000 W: 3906 L: 2176 D: 13918
FREE Ukraine!
Chess engines and dedicated chess computers fan since 1981 Mac mini M1 8GB-256GB, Windows 11 & Ubuntu ARM64.
ProteusSF Dev Forum TROLLS KINDERGARTEN
ProteusSF Dev Forum TROLLS KINDERGARTEN
-
- Posts: 918
- Joined: Mon Jan 05, 2009 7:40 pm
- Location: Germany
- Full name: Engin Üstün
Re: Introducing Igel chess engine
I need a version without AVX2 support, its crashed on my old AMD FX 8350 always, there is no version since 2.6 that not crashing.
popcount yes, but not AVX please !
popcount yes, but not AVX please !
-
- Posts: 288
- Joined: Sat Jun 30, 2018 10:58 pm
- Location: Ukraine
- Full name: Volodymyr Shcherbyna
Re: Introducing Igel chess engine
Igel 3.2.0 at https://github.com/vshcherbyna/igel/releases/tag/3.2.0 (official executable binaries for Windows and IGN net).
This release brings adequate improvement in strength.
What's new:
- smaller margin for prunning quiets
- scale down eval to 1000
- history extensions only on non pv moves
- adjust scale formula
- less reductions in lmp when not improving
- negative extensions
- futility pruning improvements
- implement cutnode
- new network ign-1-9a48854b created by using prev network (ign-1-3e998e78) and re-trained with a different lambda
Regression run against Igel 3.1.0:
Long Time Control With Increment
Code: Select all
ELO | 43.53 +- 3.13 (95%)
CONF | 60.0+0.60s Threads=1 Hash=64MB
GAMES | N: 25000 W: 8152 L: 5036 D: 11812
Code: Select all
ELO | 41.22 +- 3.25 (95%)
CONF | 10.0+0.10s Threads=1 Hash=8MB
GAMES | N: 25008 W: 8572 L: 5619 D: 10817
-
- Posts: 1362
- Joined: Sat Jul 21, 2018 7:43 am
- Location: Szentendre, Hungary
- Full name: Gabor Szots
Re: Introducing Igel chess engine
Nice improvement, Voffka. Also, long awaited.
Gabor Szots
CCRL testing group
CCRL testing group
-
- Posts: 895
- Joined: Sat May 13, 2006 1:08 am
-
- Posts: 5212
- Joined: Tue Oct 20, 2020 4:18 am
- Full name: Basti Dangca
Re: Introducing Igel chess engine
Congrats for the release and improvements!voffka wrote: ↑Sat Dec 17, 2022 7:56 pm
Igel 3.2.0 at https://github.com/vshcherbyna/igel/releases/tag/3.2.0 (official executable binaries for Windows and IGN net).
This release brings adequate improvement in strength.
What's new:
- smaller margin for prunning quiets
- scale down eval to 1000
- history extensions only on non pv moves
- adjust scale formula
- less reductions in lmp when not improving
- negative extensions
- futility pruning improvements
- implement cutnode
- new network ign-1-9a48854b created by using prev network (ign-1-3e998e78) and re-trained with a different lambda
Regression run against Igel 3.1.0:
Long Time Control With Increment
Short Time Control With IncrementCode: Select all
ELO | 43.53 +- 3.13 (95%) CONF | 60.0+0.60s Threads=1 Hash=64MB GAMES | N: 25000 W: 8152 L: 5036 D: 11812
Code: Select all
ELO | 41.22 +- 3.25 (95%) CONF | 10.0+0.10s Threads=1 Hash=8MB GAMES | N: 25008 W: 8572 L: 5619 D: 10817
Any chances implementing FRC?
Basti Dangca
CCRL testing group
CCRL testing group