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

1. https://drive.google.com/drive/folders/1Xs8Ly3wjMmXjH2agrz25Zv2e5-yqQKaP?usp=sharing

2. Place under ./savedmodels/large20/

python 3.6 tensorflow/tensorflow-gpu

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 —-policy=randompolicy --model_path='./savedmodels/model--0.0.ckpt'

1. In console:

which python

add result to the headline of main.py with #! prefix.

2. Add the path of main.py to Sabaki's manage Engine with argument --mode=gtp

• AlphaGo Zero Architecture
• Supervised Training
• Self Play pipeline
• Go Text Protocol
• Sabaki Engine enabled
• Tabula rasa
• Keras implementation
• Distributed learning

*Brain Lee *Ritchie Ng *Samuel Graván *森下 健 *yuanfengpang