LCZero Accomplishments and Goals Thus Far

[jp]

I also tried a match of LCZ (the same HW and TC as above) against minimal SF9 (1 CPU, 32 MB hash, no book, no syzygy) with Noomen 2-moves openings and it was unfortunately almost absolute slaughter, around 96% for SF.

Which Noomen 2-move openings? Can you give a link?

This result doesn't seem surprising. Even minimal SF8 or SF7 or SF6 maybe's too much.

[Albert Silver]

I can confirm that:
- LCZ on GTX1060 and 1m+1s TC is now in CCRL 2900 ballpark (I tested ID228) when tested against engines in roughly 2900-3100 range,
- cuDNN version is much faster but doesn't look any stronger than OpenCL one.

I also tried a match of LCZ (the same HW and TC as above) against minimal SF9 (1 CPU, 32 MB hash, no book, no syzygy) with Noomen 2-moves openings and it was unfortunately almost absolute slaughter, around 96% for SF. I'm really curious to see how LCZ is going to overcome SF as many people seem certain it will happen. I'm not so sure that SF would go so quietly into the night.

Remember that LCZ first began self-learning in February. It is now over 2900 CCRL. That is quite incredible if you ask me.

[Dariusz Orzechowski]

I also tried a match of LCZ (the same HW and TC as above) against minimal SF9 (1 CPU, 32 MB hash, no book, no syzygy) with Noomen 2-moves openings and it was unfortunately almost absolute slaughter, around 96% for SF.

Which Noomen 2-move openings? Can you give a link?

This result doesn't seem surprising. Even minimal SF8 or SF7 or SF6 maybe's too much.

Noomen 2-move: https://www.mediafire.com/file/y7e2gg4m ... tsuite.pgn
There is also 3-move version: https://www.mediafire.com/file/7xdcwu8h ... tsuite.pgn

[Dariusz Orzechowski]

Remember that LCZ first began self-learning in February. It is now over 2900 CCRL. That is quite incredible if you ask me.

I'm not attacking so I don't know why you go on defensive here.

For me it's exciting but it's not that incredible as I was following Leela Zero in go and something similar happened there. I like playing against pure policy networks (1 playout, no search), it's a lot of fun in both chess and go. In go pure network is already around 3-4 dan level which would correspond to FM/IM level in chess I guess. I'm pretty confident it's possible to get pure network to around 5-6 dan in go and GM level in chess.

[Albert Silver]

Remember that LCZ first began self-learning in February. It is now over 2900 CCRL. That is quite incredible if you ask me.

I'm not attacking so I don't know why you go on defensive here.

I am replying to your statement that it lost to an engine that is almost 3400 CCRL. Honestly, since LCZ is currently only about 2900-3000 on a GTX1060, the match makes no sense to me.

For me it's exciting but it's not that incredible as I was following Leela Zero in go and something similar happened there. I like playing against pure policy networks (1 playout, no search), it's a lot of fun in both chess and go. In go pure network is already around 3-4 dan level which would correspond to FM/IM level in chess I guess. I'm pretty confident it's possible to get pure network to around 5-6 dan in go and GM level in chess.

I think it is already at least SuperGM level.

[Dariusz Orzechowski]

For me it's exciting but it's not that incredible as I was following Leela Zero in go and something similar happened there. I like playing against pure policy networks (1 playout, no search), it's a lot of fun in both chess and go. In go pure network is already around 3-4 dan level which would correspond to FM/IM level in chess I guess. I'm pretty confident it's possible to get pure network to around 5-6 dan in go and GM level in chess.

I think it is already at least SuperGM level.

This is just highly innacurate. Pure network is perhaps around 2000 now what makes it a very decent player anyway.

[Dann Corbit]

For me it's exciting but it's not that incredible as I was following Leela Zero in go and something similar happened there. I like playing against pure policy networks (1 playout, no search), it's a lot of fun in both chess and go. In go pure network is already around 3-4 dan level which would correspond to FM/IM level in chess I guess. I'm pretty confident it's possible to get pure network to around 5-6 dan in go and GM level in chess.

I think it is already at least SuperGM level.

This is just highly innacurate. Pure network is perhaps around 2000 now what makes it a very decent player anyway.

I think this is apples and oranges.
Albert was talking about the current state of the LCZero project and you about using a pure network.

[Dariusz Orzechowski]

For me it's exciting but it's not that incredible as I was following Leela Zero in go and something similar happened there. I like playing against pure policy networks (1 playout, no search), it's a lot of fun in both chess and go. In go pure network is already around 3-4 dan level which would correspond to FM/IM level in chess I guess. I'm pretty confident it's possible to get pure network to around 5-6 dan in go and GM level in chess.

I think it is already at least SuperGM level.

This is just highly innacurate. Pure network is perhaps around 2000 now what makes it a very decent player anyway.

I think this is apples and oranges.
Albert was talking about the current state of the LCZero project and you about using a pure network.

I have no idea how it's possible to spin it this way. He quoted what I said about pure network and answered with a statement that is demonstrably not true.

[Albert Silver]

For me it's exciting but it's not that incredible as I was following Leela Zero in go and something similar happened there. I like playing against pure policy networks (1 playout, no search), it's a lot of fun in both chess and go. In go pure network is already around 3-4 dan level which would correspond to FM/IM level in chess I guess. I'm pretty confident it's possible to get pure network to around 5-6 dan in go and GM level in chess.

I think it is already at least SuperGM level.

This is just highly innacurate. Pure network is perhaps around 2000 now what makes it a very decent player anyway.

I think this is apples and oranges.
Albert was talking about the current state of the LCZero project and you about using a pure network.

I have no idea how it's possible to spin it this way. He quoted what I said about pure network and answered with a statement that is demonstrably not true.

It is possible because you presented a match result, then quoted LCZero's strength at ~2900 CCRL, which I am pretty sure is not 2000 Elo. I also have no idea what the strength of a 'pure network' even means. If you are suggesting plain single node play with no search tree of any kind then I am sure it is MUCH weaker than 2000 Elo.

[MonteCarlo]

For me it's exciting but it's not that incredible as I was following Leela Zero in go and something similar happened there. I like playing against pure policy networks (1 playout, no search), it's a lot of fun in both chess and go. In go pure network is already around 3-4 dan level which would correspond to FM/IM level in chess I guess. I'm pretty confident it's possible to get pure network to around 5-6 dan in go and GM level in chess.

I think it is already at least SuperGM level.

This is just highly innacurate. Pure network is perhaps around 2000 now what makes it a very decent player anyway.

I think this is apples and oranges.
Albert was talking about the current state of the LCZero project and you about using a pure network.

I have no idea how it's possible to spin it this way. He quoted what I said about pure network and answered with a statement that is demonstrably not true.

It is possible because you presented a match result, then quoted LCZero's strength at ~2900 CCRL, which I am pretty sure is not 2000 Elo. I also have no idea what the strength of a 'pure network' even means. If you are suggesting plain single node play with no search tree of any kind then I am sure it is MUCH weaker than 2000 Elo.

Yes, he's talking about a 1 visit "search", as he explicitly said (and I highlighted above).

In classical time controls, sure, at 1 visit LC0 is probably not 2000 on any human scale. However, at any time control where a human has to even remotely try to match the pace of a 1 visit "search", it's likely far stronger than 2000