Congratulation to DeepMind! This is a reengineering implementation (on behalf of many other git repo in /support/) of DeepMind's Oct19th publication: [Mastering the Game of Go without Human Knowledge]. The supervised learning approach is more practical for individuals. (This repository has single purpose of education only)
This is a trial implementation of DeepMind's Oct19th publication: Mastering the Game of Go without Human Knowledge.
DeepMind release AlphaZero Teaching Go. It's a lot of fun!
Pure RL has outperformed supervised learning+RL agent
https://drive.google.com/drive/folders/1Xs8Ly3wjMmXjH2agrz25Zv2e5-yqQKaP?usp=sharing
Place under ./savedmodels/large20/
python 3.6 tensorflow/tensorflow-gpu (version 1.4, version >= 1.5 can't load trained models)
pip install -r requirement.txt
Under repo's root dir
cd data/download
chmod +x download.sh
./download.sh
It is only an example, feel free to assign your local dataset directory
python preprocess.py preprocess ./data/SGFs/kgs-*
python main.py --mode=train
python main.py --mode=gtp —-gtp_poliy=greedypolicy --model_path='./savedmodels/your_model.ckpt'
which python
add result to the headline of main.py
with #!
prefix.
main.py
to Sabaki's manage Engine with argument --mode=gtp
*Brain Lee *Ritchie Ng *Samuel Graván *森下 健 *yuanfengpang