CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
Moderators: hgm, Dann Corbit, Harvey Williamson
Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
- Eduard
- Posts: 282
- Joined: Fri Oct 26, 2018 10:58 pm
- Location: Germany
- Full name: Eduard Nemeth
- Contact:
Re: CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
Question: On which CPU is LC Zero running? Only 1 core? NO distilled network and has more than 3000 Elo?!?
Last edited by Eduard on Tue Feb 19, 2019 8:06 am, edited 3 times in total.
Re: CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
Okay.Graham Banks wrote: ↑Tue Feb 19, 2019 6:46 amThat's on 1CPU only. No GPU.Rebel wrote: ↑Tue Feb 19, 2019 5:47 amPerhaps it's an idea to include the average NPS in the name for LZ as a sort of indication of the strength of the GPU used.Code: Select all
Rank Name Rating 45 Lc0 0.20.1 w36089 64-bit 3022
Now that we are talking, are other programs now also allowed to use datafiles that add strength?
90% of coding is debugging, the other 10% is writing bugs.
- Graham Banks
- Posts: 34830
- Joined: Sun Feb 26, 2006 9:52 am
- Location: Auckland, NZ
Re: CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
Not that I'm aware of, aside from a generic opening book and tablebases.Rebel wrote: ↑Tue Feb 19, 2019 8:01 amOkay.Graham Banks wrote: ↑Tue Feb 19, 2019 6:46 amThat's on 1CPU only. No GPU.Rebel wrote: ↑Tue Feb 19, 2019 5:47 amPerhaps it's an idea to include the average NPS in the name for LZ as a sort of indication of the strength of the GPU used.Code: Select all
Rank Name Rating 45 Lc0 0.20.1 w36089 64-bit 3022
Now that we are talking, are other programs now also allowed to use datafiles that add strength?
gbanksnz at gmail.com
Re: CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
So learning files are allowed?Graham Banks wrote: ↑Tue Feb 19, 2019 9:28 amNot that I'm aware of, aside from a generic opening book and tablebases.Rebel wrote: ↑Tue Feb 19, 2019 8:01 amOkay.Graham Banks wrote: ↑Tue Feb 19, 2019 6:46 amThat's on 1CPU only. No GPU.Rebel wrote: ↑Tue Feb 19, 2019 5:47 amPerhaps it's an idea to include the average NPS in the name for LZ as a sort of indication of the strength of the GPU used.Code: Select all
Rank Name Rating 45 Lc0 0.20.1 w36089 64-bit 3022
Now that we are talking, are other programs now also allowed to use datafiles that add strength?
90% of coding is debugging, the other 10% is writing bugs.
Re: CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
Read it, thanks.
And exactly what are the network files that come with Lc0 ?
Not Learned?
90% of coding is debugging, the other 10% is writing bugs.
-
- Posts: 2631
- Joined: Thu Jun 07, 2012 9:02 pm
Re: CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
No learning is allowed during the course of running an engine. Prior fixed learning is allowed. I can't think of any examples at the moment. Any testing an engine author does prior to release is in effect learning.
I guess the exception is if the learning file is essentially an opening book, then that is a problem but things get a bit murky as well. In essence the engine is supposed to do the work and not use pre-prepared moves, except for tablebases as Graham says,
I guess the exception is if the learning file is essentially an opening book, then that is a problem but things get a bit murky as well. In essence the engine is supposed to do the work and not use pre-prepared moves, except for tablebases as Graham says,
.
Opinions expressed here are my own, and not necessarily those of the CCRL Group.
Opinions expressed here are my own, and not necessarily those of the CCRL Group.
Re: CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
Makes sense.Modern Times wrote: ↑Tue Feb 19, 2019 8:05 pmNo learning is allowed during the course of running an engine. Prior fixed learning is allowed. I can't think of any examples at the moment. Any testing an engine author does prior to release is in effect learning.
I guess the exception is if the learning file is essentially an opening book, then that is a problem but things get a bit murky as well. In essence the engine is supposed to do the work and not use pre-prepared moves, except for tablebases as Graham says,
AZ and LZ are the biggest breakthrough in the history of computer chess, never seen an elo progression of 3400 in one year, most programmers would settle for 50. I am glad to see LZ rapidly climbing in your rating list.
Nevertheless I think LZ is a game changer to your rules. LZ learns by self-play and now other engines should have the same right.
I agree with you datafiles shouldn't be opening books in disguise and the learning part (if present) should be turned off during your testing. If you plan to play 3 openings against X,Y and Z the engine is not allowed to learn from the game against X.
90% of coding is debugging, the other 10% is writing bugs.
Re: CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
There’s a difference between a traditional opening book and a LC0 network, or even LC0 sub network trained only on opening positions for say twenty moves.Rebel wrote: ↑Wed Feb 20, 2019 9:47 amMakes sense.Modern Times wrote: ↑Tue Feb 19, 2019 8:05 pmNo learning is allowed during the course of running an engine. Prior fixed learning is allowed. I can't think of any examples at the moment. Any testing an engine author does prior to release is in effect learning.
I guess the exception is if the learning file is essentially an opening book, then that is a problem but things get a bit murky as well. In essence the engine is supposed to do the work and not use pre-prepared moves, except for tablebases as Graham says,
AZ and LZ are the biggest breakthrough in the history of computer chess, never seen an elo progression of 3400 in one year, most programmers would settle for 50. I am glad to see LZ rapidly climbing in your rating list.
Nevertheless I think LZ is a game changer to your rules. LZ learns by self-play and now other engines should have the same right.
I agree with you datafiles shouldn't be opening books in disguise and the learning part (if present) should be turned off during your testing. If you plan to play 3 openings against X,Y and Z the engine is not allowed to learn from the game against X.
The traditional program absolutely knows if it is in book, and can play a book move. LC0 doesn’t know, it can’t tell from its NN if the evaluation it gets back is “opening” or not. The former plays moves with absolute reliability but no intelligence at all, its just a look up. The LC0 “lookup” is as reliable or unreliable as with any other move, opening or not. And, in practice, LC0 isn’t looking up it's NN at root and finding a book move, it’s doing a search.
*if* traditional engines were allowed to use an opening book root-NN (as opposed to a lookup book), I think that would be ok, and parallel with what LC0 does. If they were clever enoughto also give the NN a categorical output “this is or isn’t a known book move” then, why not? It wouldn’t always be correct anyway.
- hgm
- Posts: 25521
- Joined: Fri Mar 10, 2006 9:06 am
- Location: Amsterdam
- Full name: H G Muller
- Contact:
Re: CCRL 40/40, 40/4 and FRC lists updated (16th February 2019)
All .exe files are examples, aren't they? They contain the evaluation parameters that were learned/tuned by playing millions of games. LC0 learning is just tuning of its NN parameters; there is no difference between this kind of learning and tuning of any eval, (other than that the LC0 eval has more parameters). I don't know if there are any Chess engines that store their eval parameters in a separate parameter file (e.g. to facilitate tuning without having to recompile), but I know for sure that most Shogi engines do this. (E.g. for Bonanza you would have to download a >200MB file with eval parameters, in addition to the executable.)Modern Times wrote: ↑Tue Feb 19, 2019 8:05 pmNo learning is allowed during the course of running an engine. Prior fixed learning is allowed. I can't think of any examples at the moment.
Whether engine authors choose to put their program (code + data) in a single file or distribute them over several files is pretty immaterial, right? It would be easy enough to compile the network file into the LC0 executable.