3, 6, 9, 12 months?
Does it make sense to have a
Stockfish
Asmfish
Pedantfish
...
Deep learning Stockfish
Deep learning Komodo
Deep learning Houdini
...
How far away are we from deep learning Stockfish, Komodo,...
Moderators: hgm, Rebel, chrisw
-
- Posts: 598
- Joined: Sun Aug 04, 2013 1:19 pm
-
- Posts: 931
- Joined: Tue Mar 09, 2010 3:46 pm
- Location: New York
- Full name: Álvaro Begué (RuyDos)
Re: How far away are we from deep learning Stockfish, Komodo
I am confused. Is it inevitable that deep learning will be useful for top engines? What's the evidence?
-
- Posts: 273
- Joined: Wed Aug 24, 2016 9:49 pm
Re: How far away are we from deep learning Stockfish, Komodo
In my opnion we might not see deep learning at all if we still have very consistent elo improvements year after year. Using neural networks is still pretty slow and probably not quite likely to be seen in chess engines using the current hardware generation.
-
- Posts: 598
- Joined: Sun Aug 04, 2013 1:19 pm
Re: How far away are we from deep learning Stockfish, Komodo
1.Who is stronger: Stockfish 8 vs Stockfish 8 + deep learning.AlvaroBegue wrote:I am confused. Is it inevitable that deep learning will be useful for top engines? What's the evidence?
What is your opinion?
2.Take for example infinitychess tournaments:
To get the best results, Stockfish + human(=deep learning) was always better than only Stockfish.
-
- Posts: 931
- Joined: Tue Mar 09, 2010 3:46 pm
- Location: New York
- Full name: Álvaro Begué (RuyDos)
Re: How far away are we from deep learning Stockfish, Komodo
I can't form an opinion because I don't know what "Stockfish 8 + deep learning" even means. You could use a CNN as part of the evaluation function, and you might make it better, but you would also slow it down by an order of magnitude, so the resulting player would be worse. If you can think of some other way of using deep learning here, please let us know so we all know what we are talking about.Hai wrote:1.Who is stronger: Stockfish 8 vs Stockfish 8 + deep learning.AlvaroBegue wrote:I am confused. Is it inevitable that deep learning will be useful for top engines? What's the evidence?
What is your opinion?
Two objections: 1) The `human=deep learning' part of that equation is just absurd. 2) I don't think we have enough statistical evidence that the human adds anything of value.2.Take for example infinitychess tournaments:
To get the best results, Stockfish + human(=deep learning) was always better than only Stockfish.
-
- Posts: 560
- Joined: Sun Nov 08, 2015 11:10 pm
Re: How far away are we from deep learning Stockfish, Komodo
After some garage experiments, I think NN-based eval for chess is pretty much a joke even compared to current PST+MAT eval alone.
At most, it might be good for move pruning and sorting, prove me wrong.
At most, it might be good for move pruning and sorting, prove me wrong.
-
- Posts: 349
- Joined: Sat Aug 06, 2016 8:31 pm
- Location: United States
Re: How far away are we from deep learning Stockfish, Komodo
That said, I remember fondly this result as I knew these guys from local tournaments.AlvaroBegue wrote:2) I don't think we have enough statistical evidence that the human adds anything of value.
http://en.chessbase.com/post/dark-horse ... tournament
-
- Posts: 1334
- Joined: Sun Jul 17, 2011 11:14 am
Re: How far away are we from deep learning Stockfish, Komodo
Gladly.noobpwnftw wrote:After some garage experiments, I think NN-based eval for chess is pretty much a joke even compared to current PST+MAT eval alone.
At most, it might be good for move pruning and sorting, prove me wrong.
I don't think the answer to "Are neural networks feasible for computer chess?" is "No", I think it's "Not yet".
AlphaGo required specialised hardware to win at Go, remember.
Some believe in the almighty dollar.
I believe in the almighty printf statement.
I believe in the almighty printf statement.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: How far away are we from deep learning Stockfish, Komodo
Answer is No and Never. Bojun is 100% correct.ZirconiumX wrote:Gladly.noobpwnftw wrote:After some garage experiments, I think NN-based eval for chess is pretty much a joke even compared to current PST+MAT eval alone.
At most, it might be good for move pruning and sorting, prove me wrong.
I don't think the answer to "Are neural networks feasible for computer chess?" is "No", I think it's "Not yet".
AlphaGo required specialised hardware to win at Go, remember.
If you took Giraffe and replaced its eval with SFs eval it would gain few hundred Elo easily.
Similarity between Go and chess is that they are both played at the board. That's exactly where any similarity ends.
So mentioning Go in context of chess is absolutely pointless.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: How far away are we from deep learning Stockfish, Komodo
Are you for real?Hai wrote:1.Who is stronger: Stockfish 8 vs Stockfish 8 + deep learning.AlvaroBegue wrote:I am confused. Is it inevitable that deep learning will be useful for top engines? What's the evidence?
What is your opinion?
2.Take for example infinitychess tournaments:
To get the best results, Stockfish + human(=deep learning) was always better than only Stockfish.
This is programming forum for god sake.
Human=deep learning????
Humans have much less similarity with deep learning than spiders or ants or bees.
Unfortunately bee+SF is still stronger than deep learning+SF because bee would not make Stockfish weaker while deep learning certainly would.