Poker-AI.org

Re: Releasing my solver code

2019-08-14T07:39:49+00:00

He's fuk**n Genius, )) Dude it's amazing!

Statistics: Posted by Alex89 — Wed Aug 14, 2019 7:39 am

Re: Releasing my solver code

2019-08-06T05:53:38+00:00

HontoNiBaka wrote:

Great work. I am working on a similar project, really the CFR algorithms are something I just implement from papers and hope to forget soon. But if you need help with C++ I would be happy to help, it can be quite weird coming from Java.

I actually got my c++ implementation done. I did a lot of optimizing and it’s 30-50% faster than piosolver on turn subgames and 10% slower than piosolver for for flop subgames (not sure why flop subgames are so much slower). My trees take 2-4x as much memory as piosolver though, depending on the number of bet sizes, so i’m working on compression.

Statistics: Posted by Fossana — Tue Aug 06, 2019 5:53 am

Re: Releasing my solver code

2019-08-04T19:05:32+00:00

Statistics: Posted by HontoNiBaka — Sun Aug 04, 2019 7:05 pm

Re: Releasing my solver code

2019-08-01T05:39:09+00:00

Excelent work,dude

Statistics: Posted by Knightenno — Thu Aug 01, 2019 5:39 am

Re: Releasing my solver code

2019-07-17T05:36:30+00:00

Good man.

Statistics: Posted by spears — Wed Jul 17, 2019 5:36 am

Releasing my solver code

2019-07-17T03:01:02+00:00

I've written a solver that solves turn and river subgames with limited bet size options like commercial solvers (e.g. piosolver, Simple Postflop, GTO+). I went with an implementation of discounted cfr, which is very similar to cfr+. My code is multi-threaded and written in Java. It could easily be modified to solve flop subgames. Currently I'm working on a c++ implementation to get more speed (my solver is 50% slower than piosolver, at least in the few tests I've ran).

Here's the repository: https://github.com/Fossana/discounted-cfr-poker-solver

Hope this helps!

Statistics: Posted by Fossana — Wed Jul 17, 2019 3:01 am