LizardFish 0.1 NNUE now available

[dkappe]

After the big snafu from earlier, here LizardFish 0.1, trained on only 6 million games. Somewhere between the last Texel and Komodo 13 in strength. https://www.patreon.com/posts/39496596

[matejst]

Thanks, Dietrich. I hope this time it will be OK.

Meanwhile, to answer a question you asked on Discord, a lot of engines are stronger than Komodo (and SF) at depth 8: probably Hiarcs, Gandalf 7, even Pro Deo. A net trained on Benjamin depth 8 could be very intriguing.

[lkaufman]

Thanks, Dietrich. I hope this time it will be OK.

Meanwhile, to answer a question you asked on Discord, a lot of engines are stronger than Komodo (and SF) at depth 8: probably Hiarcs, Gandalf 7, even Pro Deo. A net trained on Benjamin depth 8 could be very intriguing.

Probably this is just because Komodo reduces much more heavily than most other engines (excluding Stockfish). If you just set Use LMR in Komodo to false, it should improve a huge amount at depth 8. But if you want stronger play for the same amount of time, just using depth 9 instead is probably better. I don't know whether more depth or turning off LMR would be better for training a net.

[Rebel]

After the big snafu from earlier, here LizardFish 0.1, trained on only 6 million games. Somewhere between the last Texel and Komodo 13 in strength. https://www.patreon.com/posts/39496596

Very interesting, the Lc0 training method is quite different than the SF and Komodo *.bin approach, see the link.

http://rebel13.nl/html/nn.html

[Rebel]

Thanks, Dietrich. I hope this time it will be OK.

Meanwhile, to answer a question you asked on Discord, a lot of engines are stronger than Komodo (and SF) at depth 8: probably Hiarcs, Gandalf 7, even Pro Deo. A net trained on Benjamin depth 8 could be very intriguing.

yes, Yes, YES.......

[matejst]

Thanks, Dietrich. I hope this time it will be OK.

Meanwhile, to answer a question you asked on Discord, a lot of engines are stronger than Komodo (and SF) at depth 8: probably Hiarcs, Gandalf 7, even Pro Deo. A net trained on Benjamin depth 8 could be very intriguing.

Probably this is just because Komodo reduces much more heavily than most other engines (excluding Stockfish). If you just set Use LMR in Komodo to false, it should improve a huge amount at depth 8. But if you want stronger play for the same amount of time, just using depth 9 instead is probably better. I don't know whether more depth or turning off LMR would be better for training a net.

Larry, Ed Shroeder made multiple tests with different depths (you can find them on his site) and, yes, it is the most probable reason. But it seems also that the evaluation of these engines is better adapted to lower depths.

[matejst]

After the big snafu from earlier, here LizardFish 0.1, trained on only 6 million games. Somewhere between the last Texel and Komodo 13 in strength. https://www.patreon.com/posts/39496596

So far, although far from conclusive, it seems closer to the upper limit. It was better than RubiChess 1.7.3 and Komodo 11 in short matches at 2'2".

[dkappe]

Thanks, Dietrich. I hope this time it will be OK.

Meanwhile, to answer a question you asked on Discord, a lot of engines are stronger than Komodo (and SF) at depth 8: probably Hiarcs, Gandalf 7, even Pro Deo. A net trained on Benjamin depth 8 could be very intriguing.

yes, Yes, YES.......

You have a Benjamin linux executable?

[Rebel]

Thanks, Dietrich. I hope this time it will be OK.

Meanwhile, to answer a question you asked on Discord, a lot of engines are stronger than Komodo (and SF) at depth 8: probably Hiarcs, Gandalf 7, even Pro Deo. A net trained on Benjamin depth 8 could be very intriguing.

yes, Yes, YES.......

You have a Benjamin linux executable?

Unfortunately not.

[dkappe]

You have a Benjamin linux executable?

Unfortunately not.

I might be able to run a Windows one in WINE. Right now I’m generating some data for Toga II 4.01. It’s rattling and wheezing it’s way to d8 with lots of extra nodes.