mjai-reviewer VS rlcard

There is this website that can analyse your games here. https://mjai.ekyu.moe

This site is pretty helpful in analyzing your games using an AI mahjong program: https://mjai.ekyu.moe/

You can use Akochan to review your games. It isn't perfect and it doesn't give you a reason why your choice is not the best like a chess engine.

There are plenty of things you can do on your own to become a better mahjong player, though. Log review your games with an AI like Mortal or Naga, or with stronger players. There are also a couple of English translated higher level resources for improving your mahjong gameplay, like Uzaku's guide to tile efficiency and WWYD problem books, and Statistical Mahjong Strategy.

This would be an interesting one to run through Mortal.

This is all just what I would do though. If you want a more definitive answer you can throw your game log in to an AI like Mortal or akochan and they'll tell you how strongly they feel about a riichi.

https://mjai.ekyu.moe/ hope this gonna be useful for you

There is a website that can analyse your games and give you what should be discarded based on EV, but its currently under maintenance (https://mjai.ekyu.moe/), if you don't want to wait for it get off maintenance you can just download the program to analyse your games but its not very user friendly: https://github.com/Equim-chan/mjai-reviewer

Hi. I’ve decided to do a project to adapt an rl library to support self-play. This is a project so I can teach myself more about building rl systems. I’ve been considering working with the environment system from rlcard https://github.com/datamllab/rlcard/ but wonder if there are other more widely-used self play environment libraries. Thanks.

Can you point me to some active forums for poker bot building? I can only find github repo like https://github.com/datamllab/rlcard, which is mostly reinforcement learning. Whereas SoTA approach like Pluribus is more about game theory.

Build a Poker bot with RLCard

Probably the easiest way for you to get started is to implement your game on an open source RL framework that has working implementations of some basic CFR variations as well as some other self-play algorithms such as NFSP. OpenSpiel and RLCard are two that I am aware of. Depending on the complexity of your game and how strong your agent needs to play, you might be satisfied with the performance you get using by one of these frameworks.