AlphaZero Gomoku Save

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

Project README


This is an implementation of the AlphaZero algorithm for playing the simple board game Gomoku (also called Gobang or Five in a Row) from pure self-play training. The game Gomoku is much simpler than Go or chess, so that we can focus on the training scheme of AlphaZero and obtain a pretty good AI model on a single PC in a few hours.


  1. AlphaZero: Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
  2. AlphaGo Zero: Mastering the game of Go without human knowledge

Update 2018.2.24: supports training with TensorFlow!

Update 2018.1.17: supports training with PyTorch!

Example Games Between Trained Models

  • Each move with 400 MCTS playouts:


To play with the trained AI models, only need:

  • Python >= 2.7
  • Numpy >= 1.11

To train the AI model from scratch, further need, either:

  • Theano >= 0.7 and Lasagne >= 0.1
  • PyTorch >= 0.2.0
  • TensorFlow

PS: if your Theano's version > 0.7, please follow this issue to install Lasagne,
otherwise, force pip to downgrade Theano to 0.7 pip install --upgrade theano==0.7.0

If you would like to train the model using other DL frameworks, you only need to rewrite

Getting Started

To play with provided models, run the following script from the directory:


You may modify to try different provided models or the pure MCTS.

To train the AI model from scratch, with Theano and Lasagne, directly run:


With PyTorch or TensorFlow, first modify the file, i.e., comment the line

from policy_value_net import PolicyValueNet  # Theano and Lasagne

and uncomment the line

# from policy_value_net_pytorch import PolicyValueNet  # Pytorch
# from policy_value_net_tensorflow import PolicyValueNet # Tensorflow

and then execute: python (To use GPU in PyTorch, set use_gpu=True and use return loss.item(), entropy.item() in function train_step in if your pytorch version is greater than 0.5)

The models (best_policy.model and current_policy.model) will be saved every a few updates (default 50).

Note: the 4 provided models were trained using Theano/Lasagne, to use them with PyTorch, please refer to issue 5.

Tips for training:

  1. It is good to start with a 6 * 6 board and 4 in a row. For this case, we may obtain a reasonably good model within 500~1000 self-play games in about 2 hours.
  2. For the case of 8 * 8 board and 5 in a row, it may need 2000~3000 self-play games to get a good model, and it may take about 2 days on a single PC.

Further reading

My article describing some details about the implementation in Chinese:

Open Source Agenda is not affiliated with "AlphaZero Gomoku" Project. README Source: junxiaosong/AlphaZero_Gomoku

Open Source Agenda Badge

Open Source Agenda Rating