Dou Di Zhu with Combinational Q-Learning
Combinational Q-Learning for Dou Di Zhu
上交的一篇关于斗地主论文及相关代码。其中值得注意的环境配置
1. conda的安装与使用
wget -c https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
2 安装pybind11 pybind11 安装
2.1 安装依赖的pytest
pip install pytest
2.2 Get pybind11, from website: https://github.com/pybind/pybind11 to get the source package.
wget https://github.com/pybind/pybind11/archive/v2.4.3.tar.gz
$ tar xvf pybind11-2.4.3.tar.gz
$cd pybind11-2.4.3
$ mkdir build
$ cd build
$ cmake ..
$ make check -j 4 (make and check, not necessary)
$ sudo make install (maybe should disable python3 in /usr/bin/ if you use python2)
3. Step by step training tutorial
3.1 Clone the repo
git clone https://github.com/qq456cvb/doudizhu-C.git
3.2 Change work directory to root
cd doudizhu-C
3.3 Create env from environment.yml
conda env create -f environment.yml
3.4 Activate env
conda activate doudizhu
3.5 Build C++ files
mkdir build
cd build
cmake ..
make
3.6 Have fun training!
cd TensorPack/MA_Hierarchical_Q
python main.py