AlphaZero vs. the human brain

Discussion of anything and everything relating to chess playing software and machines.

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
User avatar
Laskos
Posts: 9442
Joined: Wed Jul 26, 2006 8:21 pm
Full name: Kai Laskos

Re: AlphaZero vs. the human brain

Post by Laskos » Sun Oct 20, 2019 9:57 am

shrapnel wrote:
Sun Oct 20, 2019 8:23 am
corres wrote:
Sat Oct 19, 2019 5:47 pm
Alone the bigger size is not a guarantee for better play.
Coupled with a strong GPU like 2080 or 2080 Ti or even two of them together, it IS.
Master Om gave you the link, try them, the last one is best I think.
Even the 32 Cores Players will be unable to beat you, if you use this Network, at least not easily, given at least a reasonably good Book and a 2080 or 2080 Ti.
No, there is a sweet spot where larger is not better. On 2080 Ti, 320x24 is better than 256x20 only in blitz and longer time control, not in bullet or faster. Larger nets do scale better with hardware and time control. I guess this 384x30 net can be the strongest only at some VERY long time controls, like 1 hour/move on an RTX GPU. Also, the strength is not well defined. I seem to have observed comparing best 256x20 and 320x24 nets, that in a direct match, larger net beats the smaller starting with some 5s/move, but against Stockfish it can perform worse, and performs better only at LTC. I am checking right now this. The problem with larger 320x24 nets with RTX GPU for Lc0 is that they tactically catch up only with very much time allotted, and at blitz TC are vulnerable against Stockfish tactical shots. Larger nets are positionally indeed better, but they need much more time for tactics.

Here are results from test suites, the best nets of their size, RTX 2070 GPU:

10s/position

256x20 T40B.4-200 net:
positional: score=157/200 [averages on correct positions: depth=4.6 time=0.87 nodes=18890]
tactical: score=121/199 [averages on correct positions: depth=7.1 time=0.95 nodes=13717]

320x24 J13B.4-150 net:
positional: score=160/200 [averages on correct positions: depth=4.9 time=1.11 nodes=9742]
tactical: score=108/199 [averages on correct positions: depth=6.3 time=1.35 nodes=7927]

Now a blitz gauntlet against Sockfish compares them.

User avatar
Master Om
Posts: 330
Joined: Wed Nov 24, 2010 9:57 am
Location: INDIA

Re: AlphaZero vs. the human brain

Post by Master Om » Sun Oct 20, 2019 5:00 pm

Laskos wrote:
Sun Oct 20, 2019 9:57 am
shrapnel wrote:
Sun Oct 20, 2019 8:23 am
corres wrote:
Sat Oct 19, 2019 5:47 pm
Alone the bigger size is not a guarantee for better play.
Coupled with a strong GPU like 2080 or 2080 Ti or even two of them together, it IS.
Master Om gave you the link, try them, the last one is best I think.
Even the 32 Cores Players will be unable to beat you, if you use this Network, at least not easily, given at least a reasonably good Book and a 2080 or 2080 Ti.
No, there is a sweet spot where larger is not better. On 2080 Ti, 320x24 is better than 256x20 only in blitz and longer time control, not in bullet or faster. Larger nets do scale better with hardware and time control. I guess this 384x30 net can be the strongest only at some VERY long time controls, like 1 hour/move on an RTX GPU. Also, the strength is not well defined. I seem to have observed comparing best 256x20 and 320x24 nets, that in a direct match, larger net beats the smaller starting with some 5s/move, but against Stockfish it can perform worse, and performs better only at LTC. I am checking right now this. The problem with larger 320x24 nets with RTX GPU for Lc0 is that they tactically catch up only with very much time allotted, and at blitz TC are vulnerable against Stockfish tactical shots. Larger nets are positionally indeed better, but they need much more time for tactics.

Here are results from test suites, the best nets of their size, RTX 2070 GPU:

10s/position

256x20 T40B.4-200 net:
positional: score=157/200 [averages on correct positions: depth=4.6 time=0.87 nodes=18890]
tactical: score=121/199 [averages on correct positions: depth=7.1 time=0.95 nodes=13717]

320x24 J13B.4-150 net:
positional: score=160/200 [averages on correct positions: depth=4.9 time=1.11 nodes=9742]
tactical: score=108/199 [averages on correct positions: depth=6.3 time=1.35 nodes=7927]

Now a blitz gauntlet against Sockfish compares them.
On a slow GPU like GTX 1050 Ti which net will be good where amount of time it runs is ample?
Always Expect the Unexpected

User avatar
Laskos
Posts: 9442
Joined: Wed Jul 26, 2006 8:21 pm
Full name: Kai Laskos

Re: AlphaZero vs. the human brain

Post by Laskos » Sun Oct 20, 2019 6:54 pm

Master Om wrote:
Sun Oct 20, 2019 5:00 pm
Laskos wrote:
Sun Oct 20, 2019 9:57 am
shrapnel wrote:
Sun Oct 20, 2019 8:23 am
corres wrote:
Sat Oct 19, 2019 5:47 pm
Alone the bigger size is not a guarantee for better play.
Coupled with a strong GPU like 2080 or 2080 Ti or even two of them together, it IS.
Master Om gave you the link, try them, the last one is best I think.
Even the 32 Cores Players will be unable to beat you, if you use this Network, at least not easily, given at least a reasonably good Book and a 2080 or 2080 Ti.
No, there is a sweet spot where larger is not better. On 2080 Ti, 320x24 is better than 256x20 only in blitz and longer time control, not in bullet or faster. Larger nets do scale better with hardware and time control. I guess this 384x30 net can be the strongest only at some VERY long time controls, like 1 hour/move on an RTX GPU. Also, the strength is not well defined. I seem to have observed comparing best 256x20 and 320x24 nets, that in a direct match, larger net beats the smaller starting with some 5s/move, but against Stockfish it can perform worse, and performs better only at LTC. I am checking right now this. The problem with larger 320x24 nets with RTX GPU for Lc0 is that they tactically catch up only with very much time allotted, and at blitz TC are vulnerable against Stockfish tactical shots. Larger nets are positionally indeed better, but they need much more time for tactics.

Here are results from test suites, the best nets of their size, RTX 2070 GPU:

10s/position

256x20 T40B.4-200 net:
positional: score=157/200 [averages on correct positions: depth=4.6 time=0.87 nodes=18890]
tactical: score=121/199 [averages on correct positions: depth=7.1 time=0.95 nodes=13717]

320x24 J13B.4-150 net:
positional: score=160/200 [averages on correct positions: depth=4.9 time=1.11 nodes=9742]
tactical: score=108/199 [averages on correct positions: depth=6.3 time=1.35 nodes=7927]

Now a blitz gauntlet against Sockfish compares them.
On a slow GPU like GTX 1050 Ti which net will be good where amount of time it runs is ample?
Probably 256x20 net (B4 run of JHorthos) up to 10 minutes runs. Longer runs than that, probably 320x24 net (again B4 of JHorthos).

User avatar
Master Om
Posts: 330
Joined: Wed Nov 24, 2010 9:57 am
Location: INDIA

Re: AlphaZero vs. the human brain

Post by Master Om » Mon Oct 21, 2019 12:35 pm

Laskos wrote:
Sun Oct 20, 2019 6:54 pm
Master Om wrote:
Sun Oct 20, 2019 5:00 pm
Laskos wrote:
Sun Oct 20, 2019 9:57 am
shrapnel wrote:
Sun Oct 20, 2019 8:23 am
corres wrote:
Sat Oct 19, 2019 5:47 pm
Alone the bigger size is not a guarantee for better play.
Coupled with a strong GPU like 2080 or 2080 Ti or even two of them together, it IS.
Master Om gave you the link, try them, the last one is best I think.
Even the 32 Cores Players will be unable to beat you, if you use this Network, at least not easily, given at least a reasonably good Book and a 2080 or 2080 Ti.
No, there is a sweet spot where larger is not better. On 2080 Ti, 320x24 is better than 256x20 only in blitz and longer time control, not in bullet or faster. Larger nets do scale better with hardware and time control. I guess this 384x30 net can be the strongest only at some VERY long time controls, like 1 hour/move on an RTX GPU. Also, the strength is not well defined. I seem to have observed comparing best 256x20 and 320x24 nets, that in a direct match, larger net beats the smaller starting with some 5s/move, but against Stockfish it can perform worse, and performs better only at LTC. I am checking right now this. The problem with larger 320x24 nets with RTX GPU for Lc0 is that they tactically catch up only with very much time allotted, and at blitz TC are vulnerable against Stockfish tactical shots. Larger nets are positionally indeed better, but they need much more time for tactics.

Here are results from test suites, the best nets of their size, RTX 2070 GPU:

10s/position

256x20 T40B.4-200 net:
positional: score=157/200 [averages on correct positions: depth=4.6 time=0.87 nodes=18890]
tactical: score=121/199 [averages on correct positions: depth=7.1 time=0.95 nodes=13717]

320x24 J13B.4-150 net:
positional: score=160/200 [averages on correct positions: depth=4.9 time=1.11 nodes=9742]
tactical: score=108/199 [averages on correct positions: depth=6.3 time=1.35 nodes=7927]

Now a blitz gauntlet against Sockfish compares them.
On a slow GPU like GTX 1050 Ti which net will be good where amount of time it runs is ample?
Probably 256x20 net (B4 run of JHorthos) up to 10 minutes runs. Longer runs than that, probably 320x24 net (again B4 of JHorthos).
Okay thanks.
Always Expect the Unexpected

Jouni
Posts: 2005
Joined: Wed Mar 08, 2006 7:15 pm

Re: AlphaZero vs. the human brain

Post by Jouni » Mon Oct 21, 2019 3:46 pm

Has human GMs so far learned something new from NN engines!?
Jouni

User avatar
Ovyron
Posts: 2706
Joined: Tue Jul 03, 2007 2:30 am

Re: AlphaZero vs. the human brain

Post by Ovyron » Mon Oct 21, 2019 8:59 pm

Jouni wrote:
Mon Oct 21, 2019 3:46 pm
Has human GMs so far learned something new from NN engines!?
Yes, the concept of "thorn pawn", where you leave an uncapturable pawn on your sixth rank, often near the opponent's king, to block and cripple the opponent, was used by Leela early on to beat the strongest A/B engines, in the times where wins by Leela were rare and noteworthy (and it was playing in a style "out of this world", at least on those games it won.)

This concept was picked up by human GMs to beat their opponents much more frequently since then (if even the strongest chess engines had a problem with the concept, it could work against humans, and it did.) Not that the concept was new, but it became mainstream thanks to Youtuber Kingscrusher, who also helped make Leela herself mainstream (and the proof is, that many people think these kind of pawns are called "fawn pawns." Why? Because of Kingscrusher's thick accent where "thorn" sounds like "fawn"!)

Since then you can even buy thorn pawn t-shirts.

Other than this and some opening novelties Leela discovered that were played by human GMs later on, I think this is it.
Great spirits have always encountered violent opposition from mediocre minds.

Post Reply