Right now, AllieStein has taken Stockfish out behind the woodshed and given the poor fishy the business. He put the fish on a stick, smoked it with some nice hickory wood, and started chewing on his ribs.
We are more than a few games into the tournament. If mighty SF wants to finish on the podium, he had better swim upstream a little harder.
The NN engines bear their mighty arm. The AB engines signal loud alarm. Maybe they will come to harm. But the NN guys are coming, in a swarm.
Rise of the mighty NN
Moderators: hgm, Rebel, chrisw
-
- Posts: 12538
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Rise of the mighty NN
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 12538
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: Rise of the mighty NN
SF has a few tricks up his fishy little sleeve, as he pulled out a very impressive draw
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 1796
- Joined: Thu Sep 18, 2008 10:24 pm
Re: Rise of the mighty NN
Except in the endgame. Then it's the other way around.Dann Corbit wrote: ↑Sun May 31, 2020 8:42 am Right now, AllieStein has taken Stockfish out behind the woodshed and given the poor fishy the business. He put the fish on a stick, smoked it with some nice hickory wood, and started chewing on his ribs.
We are more than a few games into the tournament. If mighty SF wants to finish on the podium, he had better swim upstream a little harder.
The NN engines bear their mighty arm. The AB engines signal loud alarm. Maybe they will come to harm. But the NN guys are coming, in a swarm.
I'd have expected NNs to be great in the endgame because of all the rules and principles but it doesn't seem to work.
-
- Posts: 12538
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: Rise of the mighty NN
Depth is the Achille's heel of NN programs.
In the endgame low branch factor programs like SF get absurd depths, while NN programs struggle mightily.
Look at the TB hits figures.
I like to put it this way:
In the end game, programs like SF spend most of their time talking to God (EGTB are flawless) while the NN engines fumble forward with merely superhuman strength.
In the endgame low branch factor programs like SF get absurd depths, while NN programs struggle mightily.
Look at the TB hits figures.
I like to put it this way:
In the end game, programs like SF spend most of their time talking to God (EGTB are flawless) while the NN engines fumble forward with merely superhuman strength.
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 1796
- Joined: Thu Sep 18, 2008 10:24 pm
Re: Rise of the mighty NN
Yes that's a poignant way of putting it.Dann Corbit wrote: ↑Sun May 31, 2020 11:40 am Depth is the Achille's heel of NN programs.
In the endgame low branch factor programs like SF get absurd depths, while NN programs struggle mightily.
Look at the TB hits figures.
I like to put it this way:
In the end game, programs like SF spend most of their time talking to God (EGTB are flawless) while the NN engines fumble forward with merely superhuman strength.
However, would the AB still be better in the endgame if TBs were disabled? Assuming they would, what is the issue now?
-
- Posts: 12538
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: Rise of the mighty NN
the issue now is depth of search
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 1796
- Joined: Thu Sep 18, 2008 10:24 pm
Re: Rise of the mighty NN
OK, but consider the ending K+B+N v K which some have said causes NN trouble (I haven't tested this btw)
My Mephisto Vancouver 68000 barely managed 1000 n/s and performs this endgame very well.
I myself barely manage 1 n/s and look hardly 3-5 plies ahead but I can win this in my sleep.
I would have thought a pattern recognising NN would also win with no trouble.
Is the issue that in the search (rollouts?) the NN sees that a high % of its internal games win which masks there may be a drawing line?
-
- Posts: 2283
- Joined: Sat Jun 02, 2012 2:13 am
Re: Rise of the mighty NN
Good question, Werewolf, I've often wondered about that myself. Maybe specific training on endings like what I assume dkappe is doing with Ender might be a solution.
-
- Posts: 708
- Joined: Mon Jan 16, 2012 6:34 am
Re: Rise of the mighty NN
I am pretty sure current Leela can easily mate KBN vs K endgame without tablebases.( Current SV Leela is a super feeded training data from combination of T40( 60 millions games) +T60 + further training).Werewolf wrote: ↑Mon Jun 01, 2020 8:53 amOK, but consider the ending K+B+N v K which some have said causes NN trouble (I haven't tested this btw)
My Mephisto Vancouver 68000 barely managed 1000 n/s and performs this endgame very well.
I myself barely manage 1 n/s and look hardly 3-5 plies ahead but I can win this in my sleep.
I would have thought a pattern recognising NN would also win with no trouble.
Is the issue that in the search (rollouts?) the NN sees that a high % of its internal games win which masks there may be a drawing line?
Afaik, Leela could do KNB vs K checkmate around 5~10 million training since T40.
-
- Posts: 1796
- Joined: Thu Sep 18, 2008 10:24 pm
Re: Rise of the mighty NN
Fair enough, but this was just a specific example.Nay Lin Tun wrote: ↑Tue Jun 02, 2020 4:33 amI am pretty sure current Leela can easily mate KBN vs K endgame without tablebases.( Current SV Leela is a super feeded training data from combination of T40( 60 millions games) +T60 + further training).Werewolf wrote: ↑Mon Jun 01, 2020 8:53 amOK, but consider the ending K+B+N v K which some have said causes NN trouble (I haven't tested this btw)
My Mephisto Vancouver 68000 barely managed 1000 n/s and performs this endgame very well.
I myself barely manage 1 n/s and look hardly 3-5 plies ahead but I can win this in my sleep.
I would have thought a pattern recognising NN would also win with no trouble.
Is the issue that in the search (rollouts?) the NN sees that a high % of its internal games win which masks there may be a drawing line?
Afaik, Leela could do KNB vs K checkmate around 5~10 million training since T40.