AlphaGOZero (python tensorflow implementation)

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!

---

From Paper

Pure RL has outperformed supervised learning+RL agent

Nov20 SL evaluation

Download trained model

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

2. Place under ./savedmodels/large20/

---

Set up

Install requirement

python 3.6 tensorflow/tensorflow-gpu

pip install -r requirement.txt

Download Dataset (kgs 4dan)

Under repo's root dir

cd data/download
chmod +x download.sh
./download.sh

Preprocess Data

It is only an example, feel free to assign your local dataset directory

python preprocess.py preprocess ./data/SGFs/kgs-*

Train A Model

python main.py --mode=train

Play Against An A.I. (currently only random A.I. is available)

python main.py --mode=gtp —-policy=randompolicy --model_path='./savedmodels/model--0.0.ckpt'

Play in Sabaki

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

TODO:

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

Credit (orderless):

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