Solving Large Imperfect Information Games Using CFR+ · HackerPapers discussions

Solving Large Imperfect Information Games Using CFR+ — mentioned by mastazi

Wed, 15 Sep 2021 09:43:27 GMT

> It was a shame there was the whole thing of losing the source code Yes, I can remember that very well! Eventually Oskari rebuilt the app basically from scratch, using .NET (at least IIRC) and that's what you get today if you go to the site and download it. It's not the original app but it maintains the same API for modules. Oskari nowadays is a researcher and he published some interesting articles: https://arxiv.org/abs/1407.5042 > Have you tried Drambo on iOS? Nice, thank you! I had never heard of it but after watching a couple of YouTube videos I decided I'm going to download it

Paper and discussion history. A mention is not an endorsement.

Solving Large Imperfect Information Games Using CFR+ — mentioned by mastazi

Thu, 16 Mar 2017 23:28:36 GMT

With regards to Texas Hold'em, Conterfactual Regret Optimisation [1][2] was already able to beat humans in limit games, while it seems that this new approach is able to do the same in no-limit games. My naive understanding is that no-limit games are harder to crack because there are more possible outcomes, thus the available information (poker is an "imperfect information" game) becomes "even more imperfect". [1] https://arxiv.org/abs/1407.5042 (yes, the author is the same Oskari Tammelin who created Jeskola Buzz, a popular piece of music software). [2]…

Paper and discussion history. A mention is not an endorsement.

Solving Large Imperfect Information Games Using CFR+ — mentioned by mastazi

Wed, 11 Jan 2017 00:29:09 GMT

This is completely OT but I just googled about the topic of "solving" Texas Hold'em Poker and other imperfect information games and discovered that one of the contributors to the research on Counterfactual Regret Minimization algorithms, developed at the University of Alberta[0], is Oskari Tammelin[1] who also created, in the late 90s, my favourite piece of music software, Jeskola Buzz[2]. His personal website[3] contains pages on both topics. [0] http://poker.srv.ualberta.ca/about [1] https://arxiv.org/abs/1407.5042 [2] https://en.wikipedia.org/wiki/Jeskola_Buzz [3] http://jeskola.net/

Paper and discussion history. A mention is not an endorsement.