- TensorPack
- TensorFlow
- Conditional
- Pybind11
Create a folder called build.linux
(build
if you're using Windows).
Type cd build; cmake ..; make
.
Run TensorPack/MA_Hierarchical_Q/main.py
.
TensorPack
contain different RL algorithms to train agentsexperiments
contain scripts to evaluate agents' performance against other baselinessimulator
contain scripts to evaluate agents' performance against online gaming platform called "QQ Dou Di Zhu" (we provide it for academic use only, use it at your own risk!)
- We provide a Monte-Carlo-Tree-Search algorithm in https://github.com/qq456cvb/doudizhu-baseline
- We provide a configured Dou Di Zhu mini-server in https://github.com/qq456cvb/doudizhu-tornado
See our paper https://arxiv.org/pdf/1901.08925.pdf