Hello,
cf. https://sites.google.com/site/dshawul/home - http://www.sdchess.ru/engines/scorpio_2_8_6_mac_osx.zip
Regards,
Norbert
Scorpio 2.8.6 MCTS neural network evaluation
Moderators: hgm, Rebel, chrisw
-
- Posts: 1643
- Joined: Tue May 20, 2008 4:57 pm
- Location: Augsburg - Germany
-
- Posts: 3019
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: Scorpio 2.8.6 MCTS neural network evaluation
I should add that one can use Leela weights too. I have not tested beyond seeing they work.
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."
-
- Posts: 1142
- Joined: Thu Dec 28, 2017 4:06 pm
- Location: Argentina
Re: Scorpio 2.8.6 MCTS neural network evaluation
Do those provided nets (or any other net) work though? How to check if they are working or not?
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls
-
- Posts: 558
- Joined: Sat Mar 25, 2006 8:27 pm
Re: Scorpio 2.8.6 MCTS neural network evaluation
That is very surprising.Albert Silver wrote: ↑Mon Jul 23, 2018 5:39 pm I should add that one can use Leela weights too. I have not tested beyond seeing they work.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: Scorpio 2.8.6 MCTS neural network evaluation
Why would it be surprising? LC0 search is anyway total crap as it A0 search, and ppl currently involved in LC0 development clearly have not much clue how to improve or even only evaluate search performance.Robert Pope wrote: ↑Tue Jul 24, 2018 4:02 amThat is very surprising.Albert Silver wrote: ↑Mon Jul 23, 2018 5:39 pm I should add that one can use Leela weights too. I have not tested beyond seeing they work.
-
- Posts: 3186
- Joined: Sat Feb 16, 2008 7:38 am
- Full name: Peter Martan
Re: Scorpio 2.8.6 MCTS neural network evaluation
Could you give it a try, Albert?Albert Silver wrote: ↑Mon Jul 23, 2018 5:39 pm I should add that one can use Leela weights too. I have not tested beyond seeing they work.
That sounds very interesting to me!
Peter.
-
- Posts: 558
- Joined: Sat Mar 25, 2006 8:27 pm
Re: Scorpio 2.8.6 MCTS neural network evaluation
Because the weights are tied to the specific neural network implementation format of LC0. In order for them to function in another engine, that engine has to have the exact same input planes, with the same orientation, in the exact same order, in the exact same format. Otherwise, it would be like porting Stockfish evaluation weights into another engine, except you are assigning them at random. Not even all LC0 neural nets are compatible across versions of LC Zero.Milos wrote: ↑Tue Jul 24, 2018 4:59 amWhy would it be surprising? LC0 search is anyway total crap as it A0 search, and ppl currently involved in LC0 development clearly have not much clue how to improve or even only evaluate search performance.Robert Pope wrote: ↑Tue Jul 24, 2018 4:02 amThat is very surprising.Albert Silver wrote: ↑Mon Jul 23, 2018 5:39 pm I should add that one can use Leela weights too. I have not tested beyond seeing they work.
So for them to actually work in another engine is either a mind-boggling coincidence, or intentional copying of the format (not that there's anything wrong with that [/seinfeld]). IIRC, ScorpioMCTS came first, so it would be surprising to find that its neural net layout is exactly the same.
-
- Posts: 4610
- Joined: Wed Oct 01, 2008 6:33 am
- Location: Regensburg, Germany
- Full name: Guenther Simon
Re: Scorpio 2.8.6 MCTS neural network evaluation
I highly doubt this too. For me the Scorpio NN files are completely different.Robert Pope wrote: ↑Tue Jul 24, 2018 4:02 amThat is very surprising.Albert Silver wrote: ↑Mon Jul 23, 2018 5:39 pm I should add that one can use Leela weights too. I have not tested beyond seeing they work.
https://rwbc-chess.de
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: Scorpio 2.8.6 MCTS neural network evaluation
I don't think you understand how MCTS works. In Scorpio it is using just value network as direct rollout replacement (i.e. as eval). Policy network is not used to guide the search. MCTS is completely agnostic to the way evaluation only is performed (A/B rollout, handcrafted NN eval, LC0/A0 NN eval, etc.). Format, number of layers, input planes of NN and all the internals are irrelevant for search.Robert Pope wrote: ↑Tue Jul 24, 2018 5:36 pmBecause the weights are tied to the specific neural network implementation format of LC0. In order for them to function in another engine, that engine has to have the exact same input planes, with the same orientation, in the exact same order, in the exact same format. Otherwise, it would be like porting Stockfish evaluation weights into another engine, except you are assigning them at random. Not even all LC0 neural nets are compatible across versions of LC Zero.Milos wrote: ↑Tue Jul 24, 2018 4:59 amWhy would it be surprising? LC0 search is anyway total crap as it A0 search, and ppl currently involved in LC0 development clearly have not much clue how to improve or even only evaluate search performance.Robert Pope wrote: ↑Tue Jul 24, 2018 4:02 amThat is very surprising.Albert Silver wrote: ↑Mon Jul 23, 2018 5:39 pm I should add that one can use Leela weights too. I have not tested beyond seeing they work.
So for them to actually work in another engine is either a mind-boggling coincidence, or intentional copying of the format (not that there's anything wrong with that [/seinfeld]). IIRC, ScorpioMCTS came first, so it would be surprising to find that its neural net layout is exactly the same.
How efficient it is, is another question. But knowing that UCT in LC0/A0 is not very efficient it should not be too difficult to make search that would work better using the same NN from LC0/A0 for eval only.
And I am not buying this crap that policy network is enough to make efficient search with UCT from A0. Sorry, but it doesn't work that way, just because some Google guys published some crappy shady preprint.
-
- Posts: 558
- Joined: Sat Mar 25, 2006 8:27 pm
Re: Scorpio 2.8.6 MCTS neural network evaluation
Except....the value network is an output of the neural network, and is simply a series of transformations of the inputs and the weights. So of course the format of the neural network matters! If you don't have the same format, then the value network that gets output is junk. How MCTS uses that to guide the search is what is irrelevant, since it's garbage information.Milos wrote: ↑Tue Jul 24, 2018 7:12 pm I don't think you understand how MCTS works. In Scorpio it is using just value network as direct rollout replacement (i.e. as eval). Policy network is not used to guide the search. MCTS is completely agnostic to the way evaluation only is performed (A/B rollout, handcrafted NN eval, LC0/A0 NN eval, etc.). Format, number of layers, input planes of NN and all the internals are irrelevant for search.