What other depth and boost combinations have you tried? And where can I download the AH tactic tests? Thanks,Jaglo wrote: ↑Thu Mar 07, 2019 10:26 am Hi KillerDucky. Your project is very interesting. But...
The biggest weakness of LC0 is endgame and tactics. Leela handles other elements well, and in the positional game she outperforms the classic engines.
I have tested eigenmann (100 positions) and AH_tactics (250 positions). Stockfish 10 plays them almost perfectly (97/100 and 246/250).
The results of LC0 (network 32988) are 68% in both cases. ...
I have chosen those positions that LC0 can't solve (and Stockfish does). The eigenmann subset consists of 32 items. The AH_tectics subset is 79 positions. In this subset I tested Leelafish with different settings. The best results I received when:
auxengine-depth=20/25
auxengine-boost=100.00
...
Trying out the Leela Hybrid engine (NN with AB)
Moderators: hgm, Rebel, chrisw
-
- Posts: 47
- Joined: Fri Feb 15, 2019 11:41 pm
- Full name: Brent M
Re: Trying out the Leela Hybrid engine (NN with AB)
-
- Posts: 1167
- Joined: Thu Dec 25, 2008 9:07 pm
- Full name: Herbert L
Re: Trying out the Leela Hybrid engine (NN with AB)
@ sincerelybrent
AH_Endgames-250 and AH_Tactics-250 Results and epd's
http://www.talkchess.com/forum3/viewtop ... =2&t=41023
use the links in the first post
AH_Endgames-250 and AH_Tactics-250 Results and epd's
http://www.talkchess.com/forum3/viewtop ... =2&t=41023
use the links in the first post
-
- Posts: 13
- Joined: Sat Mar 02, 2019 7:45 pm
- Full name: Jacek Glowinski
Re: Trying out the Leela Hybrid engine (NN with AB)
auxengine-threshold=10/100/1000What other depth and boost combinations have you tried? And where can I download the AH tactic tests? Thanks,
auxengine-depth=15/20/25
auxengine-boost=50/100
auxengine-follow-pv-depth=4 (1? 10? - I do not remember)
I didn't check all combinations, only after the change I did a test and if it gave an improvement I moved it with other parameters, trying to achieve further improvement. A deeper depth is needed for Stockfish to find a solution at all (approx. 20-30). Setting the boost to 100 was also important. I haven't noticed the influence of other parameters.
The Eigemann website no longer exists. I once downloaded an epd and converted it to chessbase, and now I don't know how to convert it back to epd. AH_Endgames_250 should be similar.
-
- Posts: 47
- Joined: Fri Feb 15, 2019 11:41 pm
- Full name: Brent M
Re: Trying out the Leela Hybrid engine (NN with AB)
Thank you very muchPaloma wrote: ↑Thu Mar 07, 2019 7:20 pm @ sincerelybrent
AH_Endgames-250 and AH_Tactics-250 Results and epd's
http://www.talkchess.com/forum3/viewtop ... =2&t=41023
use the links in the first post
-
- Posts: 12
- Joined: Fri Mar 23, 2018 2:31 am
Re: Trying out the Leela Hybrid engine (NN with AB)
v0.21.0-fish-v0.8 released!
https://github.com/killerducky/lc0/wiki/LeelaFish
https://github.com/killerducky/lc0/releases
Important note: Stockfish 10 official release has a bug that Leelafish hits more often than normal. To workaround this: 1) Use a recent dev version (after 2018-12-16) or 2) Set Threads=1 in AuxEngineOptions.
Change notes:
* Merge Lc0 bugfix, required to run T40 nets:
* Improved folding of batch norm into weights and biases - fixes negative gamma bug. (LeelaChessZero#779)
* Now Leelafish is based off official release v0.21.0 of Lc0 (previously v0.21.0-dev).
https://github.com/killerducky/lc0/wiki/LeelaFish
https://github.com/killerducky/lc0/releases
Important note: Stockfish 10 official release has a bug that Leelafish hits more often than normal. To workaround this: 1) Use a recent dev version (after 2018-12-16) or 2) Set Threads=1 in AuxEngineOptions.
Change notes:
* Merge Lc0 bugfix, required to run T40 nets:
* Improved folding of batch norm into weights and biases - fixes negative gamma bug. (LeelaChessZero#779)
* Now Leelafish is based off official release v0.21.0 of Lc0 (previously v0.21.0-dev).
-
- Posts: 4889
- Joined: Thu Mar 09, 2006 6:34 am
- Location: Pen Argyl, Pennsylvania
Re: Trying out the Leela Hybrid engine (NN with AB)
+1 good work - appreciate it!KillerDucky wrote: ↑Thu Mar 14, 2019 1:25 am v0.21.0-fish-v0.8 released!
https://github.com/killerducky/lc0/wiki/LeelaFish
https://github.com/killerducky/lc0/releases
Important note: Stockfish 10 official release has a bug that Leelafish hits more often than normal. To workaround this: 1) Use a recent dev version (after 2018-12-16) or 2) Set Threads=1 in AuxEngineOptions.
Change notes:
* Merge Lc0 bugfix, required to run T40 nets:
* Improved folding of batch norm into weights and biases - fixes negative gamma bug. (LeelaChessZero#779)
* Now Leelafish is based off official release v0.21.0 of Lc0 (previously v0.21.0-dev).
-
- Posts: 8
- Joined: Sun Mar 03, 2019 12:46 pm
- Full name: Kalikoba
Re: Trying out the Leela Hybrid engine (NN with AB)
Nice one, and , if the auxiliary engine accepts to read and play .bin books, would it be possible to let Leelafish play its auxiliary engine book if it exists ?
-
- Posts: 13
- Joined: Sat Mar 02, 2019 7:45 pm
- Full name: Jacek Glowinski
Re: Trying out the Leela Hybrid engine (NN with AB)
Leelafish v0.8
net: 32988
auxengine=Stockfish 10 (Hash=1024;Threads=1)
auxengine-depth=25
auxengine-boost=100.00
Syzygy 345
eigenmann: 84%
Perhaps the result for the endings would have been better if the depth of analysis had not been constant, but depended on the time.
AH_tactics: 94%
Not perfect, but much better than pure LC0.
positional play (tests gcp+typp): 39/63
LC0 achieves the same result.
net: 32988
auxengine=Stockfish 10 (Hash=1024;Threads=1)
auxengine-depth=25
auxengine-boost=100.00
Syzygy 345
eigenmann: 84%
Perhaps the result for the endings would have been better if the depth of analysis had not been constant, but depended on the time.
AH_tactics: 94%
Not perfect, but much better than pure LC0.
positional play (tests gcp+typp): 39/63
LC0 achieves the same result.
-
- Posts: 12
- Joined: Fri Mar 23, 2018 2:31 am
Re: Trying out the Leela Hybrid engine (NN with AB)
I haven't used .bin books. I guess some engines (but not Stockfish?) have UCI options that allow it to use .bin? You can pass any arbitrary UCI options using AuxEngineOptions:kalikoba2019 wrote: ↑Thu Mar 14, 2019 7:03 pm Nice one, and , if the auxiliary engine accepts to read and play .bin books, would it be possible to let Leelafish play its auxiliary engine book if it exists ?
Code: Select all
AuxEngineOptions Hash1024;Threads=1;PolyglotOptionName=c:\mybook.bin
-
- Posts: 1535
- Joined: Sun Oct 25, 2009 2:30 am
Re: Trying out the Leela Hybrid engine (NN with AB)
KillerDucky wrote: ↑Fri Mar 15, 2019 12:11 amI haven't used .bin books. I guess some engines (but not Stockfish?) have UCI options that allow it to use .bin? You can pass any arbitrary UCI options using AuxEngineOptions:kalikoba2019 wrote: ↑Thu Mar 14, 2019 7:03 pm Nice one, and , if the auxiliary engine accepts to read and play .bin books, would it be possible to let Leelafish play its auxiliary engine book if it exists ?
Code: Select all
AuxEngineOptions Hash1024;Threads=1;PolyglotOptionName=c:\mybook.bin
If you pass that uci option to the auxiliary engine, won't the PV be just one move? The best move in the position according to the book? In that case, it sounds like Leelafish would just play unrestricted, just as regular Leela would. The only difference would be that it would take into account the book's best move, but the decision would rest ultimately in its own judgement. Quite far away from what a book is supposed to do.Leela uses the AuxEngine's PV to boost the Policy of those moves. Otherwise Leela's search runs the same as before, including all position evaluations.