rlcard
rlcard copied to clipboard
datamllab
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
Hey, So PettingZoo is now the third most installed RL library on PyPI and as best we can tell is the most installed multi-agent library in the world (https://pepy.tech/project/pettingzoo). One...
Hello, we have observed that the new rlcard version has made some changes that raises failures for the code in [PettingZoo](https://github.com/PettingZoo-Team/PettingZoo). We have been able to fix some of them,...
I want to implement Kuhn poker and create pull request. The documentation says that I have to inherit from classes in rlcard/core.py. However, Leduc poker is implemented by inheriting from...
First of all thanks for this great contribution, wanted to ask if there are any script for rule based model for mahjong? so i can generate data using it.
Created keras version of backjack_dqn and dqn_agent
First of all, thanks a lot for open-sourcing this excellent framework. It helped me a lot to learn RL and develop the AI strategy for my own card game. During...
Hello, was wondering if there were instructions that can facilitate supervised learning stage before RL, will be very useful in games like doudizho and mahjong, Thanks in advance.
Hey, the performance of Mahjong is becoming an issue for us, so we're starting to work on it ourselves. Do you have any recommendations on what we should be doing?
在 麻将的 Game.py 中 有 round, dealer 这俩对象， round当中又包含一个dealer，在init_game当中 先实例化了一个dealer ,然后把指针传给了 round 但是在开启了step_back之后，在step当中会用deepcopy存一下之前的内容，在step_back函数中，仅仅用了一个pop，此时的game.dealer 和 game.round.dealer 就对不上了。 所以在用cfrAgent的时候会出现错误。 目前我在step_back当中，简单改了一下 ```python self.dealer, self.players, self.round = self.history.pop() self.round.dealer = self.dealer self.round.judger = self.judger...
running `python nolimit_holdem_deepcfr.py` its stack on this possition for ever
