Search found 74 matches

by thomasahle
Thu Jan 14, 2021 12:42 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: AlphaZero
Replies: 21
Views: 8070

Re: AlphaZero

Hi Maksim,

Your assertion is correct: Logistic regression is just like a neural network/perceptron with no hidden layers.

I used FastText because it is a very fast logistic regression algorithm on sparse inputs. You could use something else too if you'd like.
by thomasahle
Sat Aug 29, 2020 10:55 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: __builtin_popcountll doesn't bring any gain
Replies: 16
Views: 4882

Re: __builtin_popcountll doesn't bring any gain

What does the "xor eax eax" instruction do? Looks like it is setting some random register to 0?
by thomasahle
Tue May 05, 2020 8:51 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: AlphaZero
Replies: 21
Views: 8070

Re: AlphaZero

Check outthe Fastchess of you're interested: https://github.com/thomasahle/fastchess . It's a python implementation of the MCTS approach in the Alpha Zero papers, and it uses the simplest "Neural" network architecture possible: A linear function from the current boolean board to the next move. (A 18...
by thomasahle
Sun Sep 15, 2019 2:52 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: New Tool for Tuning with Skopt
Replies: 61
Views: 19012

Re: New Tool for Tuning with Skopt

Once I have played a series of games and I have the file data.log, if I run the test again and use the file, in each run I have different results and the results seem quite random. This happens because summarizing works by sampling a number of random values. As far as I can see the arguments you ge...
by thomasahle
Wed Sep 11, 2019 5:09 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: New Tool for Tuning with Skopt
Replies: 61
Views: 19012

Re: New Tool for Tuning with Skopt

After trying this script a little on some search parameter I am not in success. Any advice will be welcome about choosing the good script configuration and a reasonable number of games. For now, 1000 games to tune 4 or 5 parameters at a time seems not good. People have had some problems with skopt ...
by thomasahle
Mon Sep 09, 2019 4:03 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: New Tool for Tuning with Skopt
Replies: 61
Views: 19012

Re: New Tool for Tuning with Skopt

JVMerlino wrote:
Sun Sep 08, 2019 10:44 pm
Well, Myrddin's in luck here. Since "usermove=0" is the default, I never implemented it.
Well, I didn't mean "implement" it as anything else than trying to parse unrecognised commands as moves.
by thomasahle
Sun Sep 08, 2019 9:02 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: New Tool for Tuning with Skopt
Replies: 61
Views: 19012

Re: New Tool for Tuning with Skopt

I'm trying it now, using xboard protocol, and I'm not really successful because python-chess seems to be rejecting "usermove=1". Anyone experience this before ? Yes, this is frustrating. I had to implement usermove=0 in sunfish to get it to work with python-chess. Would be great if anyone could sen...
by thomasahle
Thu Sep 05, 2019 12:19 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: New Tool for Tuning with Skopt
Replies: 61
Views: 19012

Re: New Tool for Tuning with Skopt

Currently I am running 5000 games with nodes=800 to tune 4 parameters at once. I will report the status here once it is done. Note that if you are doing that many games, it might be better to use the GBRT estimator by Jorg's experiements. This is done with the `-base-estimator GBRT` flag. See https...
by thomasahle
Mon Sep 02, 2019 12:49 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: New Tool for Tuning with Skopt
Replies: 61
Views: 19012

Re: New Tool for Tuning with Skopt

It's a nice project, but i had issues: - ahash from log file should not consider number of games and even concurrency, that way would be easy to run a 200 game session run using 100 games from previous run. - Let me use options that are not seen as UCI options, i don't wanna to expose all possible ...
by thomasahle
Sun Sep 01, 2019 1:12 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: New Tool for Tuning with Skopt
Replies: 61
Views: 19012

Re: New Tool for Tuning with Skopt

Jorg, have you tried one of the other base estimators supported by skopt/tune? They might be faster. You can "RF", "ET" or "GBRT". I'll think of other ways to speed up for many games. Maybe something like running more than 2 games for every choice of parameters. But even inverting a 2000x2000 matrix...