Alpha Gobang Zero

A gobang robot based on reinforcement learning

Policy-Value Net

• Network structure
  • ConvBlock × 1
  • ResidueBlock × 4
  • PolicyHead × 1
  • ValueHead × 1
• Network visualization

Quick start

1. Create virtual environment:

   conda create -n Alpha_Gobang_Zero python=3.8
   conda activate Alpha_Gobang_Zero
   pip install -r requirements.txt
   

2. Install PyTorch，refer to the blog for details；

3. Start game:

   conda activate Alpha_Gobang_Zero
   python game.py
   

Train model

conda activate Alpha_Gobang_Zero
python train.py

Blog

《如何使用自对弈强化学习训练一个五子棋机器人Alpha Gobang Zero》

Reference

• 《Mastering the game of Go without human knowledge》
• 《Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm》

FAQs

• Why does the window get stuck when it is dragged?

  Because the interface background uses acrylic effect, this problem will occur for some versions of win10. There are three solutions:

  • Upgrade win10 to the latest version.
  • Uncheck the check box of Advanced system settings --> Performance --> Show window contents when dragging.
  • Turn off the option to enable acrylic background in the setting interface.

• Why does the configuration I modified in the settings interface not take effect immediately?

  The modified configuration will take effect at the beginning of the next game.

License

Alpha-Gobang-Zero is licensed under GPLv3.

Copyright © 2021 by zhiyiYo.