Reinforcement-Learning-Gomoku

Requirements

• python3.10

Run

• Player agent vs AI agent: python3 server.py
• To train alphazero agent:
  • Switch to branch alphazero
  • python3 train.py to train
  • Training results are saved in ./models/base/ or in PATH defined in train.py
  • Board size is currently adjusted to 9x9 due to the limit of computing resources