TalkChess.com

This is not even hard. I have no experience constructing proof games, and I succeeded after a few minutes: [Event "Edited game"] [Site ""] [Date "2019.06.09"] [Round "-"] [White "-"] [Black "-"] [Result "*"] 1. a4 b5 2. axb5 a6 3. bxa6 Bb7 4. axb7 g5 5. bxa8=Q g4 6. h4 Bh6 7. g3 Bg5 8. hxg5 f5 9. Rh...

Is training for all the variants at the same time an option? I mean, have each minibatch contain examples from each of the variants.

Take a look here: https://www.365chess.com/opening.php

There are conditions when you can simply return a value without further search. Some ICCA paper by the authors of DarkThought in the 90s called this "interior-node recognizers": https://www.chessprogramming.org/Interior_Node_Recognizer For situations where you are not sure (say KQKB), you can still ...

Part of the problem is your coding style. Your function names are OK, but your variable names are not informative at all. I have no idea what `ts', `ns', `nd', `mt', or `m' mean. Chances are you won't know when you encounter the code in a couple of days either. You should write code that is easy for...

I understand your concern, but I suspect in practice it won't matter. Looking at enough examples, the network can figure out that strong positions for white end up being either won by white or draws the vast majority of the time, even if it doesn't know that loss < draw < win.

You don't propose an alternative, so it's hard to discuss pros and cons. However, these matters always come down to an empirical question. Having a scheme that produces distinct probabilities for the outcomes has the advantage that they can be combined however necessary when we use the network. For ...

Was a set of input planes representing a position at time (t - T + 1) oriented for the side to move at time t or time (t - T + 1)? All the history input planes are oriented for the current side to move, i.e. at time t. Would it matter if they weren’t? (That’s a serious question btw) I suppose not b...

Here's a hacked-together Perl implementation: cat kk.pgn | perl -ne ' if (/^\[/ || /^$/) {print; next;} for $token (split " ", $_) { if ($token =~ /^[1-9]/) {$wtm = 1; print "$token "; next;} if ($wtm == 0) {$token =~ s/[!\?]//g;} print "$token "; $wtm = 1-$wtm; } print "\n" ' That removes markings ...

smatovic wrote: ↑

Fri Feb 01, 2019 6:03 pm

Myself still ponders on how to combine an AlphaBeta searcher with gpgpu ann eval...

I have a promising idea for that, but I don't really have the time to implement it. My job, my wife and my kids are getting in the way of the really important stuff!