Page 1 of 5

How far away are we from deep learning Stockfish, Komodo,...

Posted: Fri May 19, 2017 10:55 am
by Hai
3, 6, 9, 12 months?

Does it make sense to have a
Stockfish
Asmfish
Pedantfish
...
Deep learning Stockfish
Deep learning Komodo
Deep learning Houdini
...

Re: How far away are we from deep learning Stockfish, Komodo

Posted: Fri May 19, 2017 11:13 am
by AlvaroBegue
I am confused. Is it inevitable that deep learning will be useful for top engines? What's the evidence?

Re: How far away are we from deep learning Stockfish, Komodo

Posted: Fri May 19, 2017 11:29 am
by CheckersGuy
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.

Re: How far away are we from deep learning Stockfish, Komodo

Posted: Fri May 19, 2017 2:59 pm
by Hai
AlvaroBegue wrote:I am confused. Is it inevitable that deep learning will be useful for top engines? What's the evidence?
1.Who is stronger: Stockfish 8 vs Stockfish 8 + deep learning.
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.

Re: How far away are we from deep learning Stockfish, Komodo

Posted: Fri May 19, 2017 8:06 pm
by AlvaroBegue
Hai wrote:
AlvaroBegue wrote:I am confused. Is it inevitable that deep learning will be useful for top engines? What's the evidence?
1.Who is stronger: Stockfish 8 vs Stockfish 8 + deep learning.
What is your opinion?
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.
2.Take for example infinitychess tournaments:
To get the best results, Stockfish + human(=deep learning) was always better than only Stockfish.
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.

Re: How far away are we from deep learning Stockfish, Komodo

Posted: Fri May 19, 2017 8:36 pm
by noobpwnftw
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.

Re: How far away are we from deep learning Stockfish, Komodo

Posted: Fri May 19, 2017 8:59 pm
by zenpawn
AlvaroBegue wrote:2) I don't think we have enough statistical evidence that the human adds anything of value.
That said, I remember fondly this result as I knew these guys from local tournaments. :)

http://en.chessbase.com/post/dark-horse ... tournament

Re: How far away are we from deep learning Stockfish, Komodo

Posted: Fri May 19, 2017 9:41 pm
by ZirconiumX
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.
Gladly.

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.

Re: How far away are we from deep learning Stockfish, Komodo

Posted: Fri May 19, 2017 11:38 pm
by Milos
ZirconiumX wrote:
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.
Gladly.

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.
Answer is No and Never. Bojun is 100% correct.
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.

Re: How far away are we from deep learning Stockfish, Komodo

Posted: Fri May 19, 2017 11:43 pm
by Milos
Hai wrote:
AlvaroBegue wrote:I am confused. Is it inevitable that deep learning will be useful for top engines? What's the evidence?
1.Who is stronger: Stockfish 8 vs Stockfish 8 + deep learning.
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.
Are you for real?
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.