This project is a Gomoku extension of the Connect4 Zero implementation by @Zeta36 at: https://github.com/Zeta36/connect4-alpha-zero

which is further based on:

1. DeepMind's Oct19th publication: Mastering the Game of Go without Human Knowledge.
2. The Reversi development of the DeepMind ideas that @mokemokechicken did in his repo: https://github.com/mokemokechicken/reversi-alpha-zero

• Python 3.6.3
• tensorflow-gpu: 1.3.0
• Keras: 2.0.8

This AlphaGo Zero implementation consists of three worker self, opt and eval.

• self is Self-Play to generate training data by self-play using BestModel.
• opt is Trainer to train model, and generate next-generation models.
• eval is Evaluator to evaluate whether the next-generation model is better than BestModel. If better, replace BestModel.

For evaluation, you can play chess with the BestModel.

• play_gui is Play Game vs BestModel using ASCII character encoding.

• data/model/model_best_*: BestModel.
• data/model/next_generation/*: next-generation models.
• data/play_data/play_*.json: generated training data.
• logs/main.log: log file.

If you want to train the model from the beginning, delete the above directories.

pip install -r requirements.txt

If you want use GPU,

pip install tensorflow-gpu

Create .env file and write this.

KERAS_BACKEND=tensorflow

For training model, execute Self-Play, Trainer and Evaluator.

python src/connect4_zero/run.py self

When executed, Self-Play will start using BestModel. If the BestModel does not exist, new random model will be created and become BestModel.

• --new: create new BestModel
• --type mini: use mini config for testing, (see src/connect4_zero/configs/mini.py)

python src/connect4_zero/run.py opt

When executed, Training will start. A base model will be loaded from latest saved next-generation model. If not existed, BestModel is used. Trained model will be saved every 2000 steps(mini-batch) after epoch.

• --type mini: use mini config for testing, (see src/connect4_zero/configs/mini.py)
• --total-step: specify total step(mini-batch) numbers. The total step affects learning rate of training.

python src/connect4_zero/run.py eval

When executed, Evaluation will start. It evaluates BestModel and the latest next-generation model by playing about 200 games. If next-generation model wins, it becomes BestModel.

• --type mini: use mini config for testing, (see src/connect4_zero/configs/mini.py)

python src/connect4_zero/run.py play_gui

When executed, ordinary chess board will be displayed in ASCII code and you can play against BestModel.

Usually the lack of memory cause warnings, not error. If error happens, try to change per_process_gpu_memory_fraction in src/worker/{evaluate.py,optimize.py,self_play.py},

tf_util.set_session_config(per_process_gpu_memory_fraction=0.2)

Less batch_size will reduce memory usage of opt. Try to change TrainerConfig#batch_size in NormalConfig.

The following table is records of the best models.