GitHub - Yoda-wu/alpha_zero_feat: 基于深度神经网络的五子棋博弈引擎设计与实现——AlphaZero项目的克隆

实验：AlphaZero-Gomoku——基于深度神经网络的五子棋博弈引擎设计与实现

本次实验是开发基于深度神经网络的五子棋引擎设计与实现。本次实验的环境如下：

启动人机对战：

python ./human_paly.py

训练模型：

python ./train.py

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
__pycache__		__pycache__
README.md		README.md
alpha_zeroI.py		alpha_zeroI.py
alpha_zeroII-model.py		alpha_zeroII-model.py
alpha_zeroII.py		alpha_zeroII.py
best_policy_10_10_5_new.model		best_policy_10_10_5_new.model
best_policy_8_8_5_new.model		best_policy_8_8_5_new.model
current_policy_10_10_5_new.model		current_policy_10_10_5_new.model
current_policy_8_8_5_new.model		current_policy_8_8_5_new.model
game.py		game.py
human_play.py		human_play.py
loss_win.log		loss_win.log
mcts_alphaZero.py		mcts_alphaZero.py
mcts_pure.py		mcts_pure.py
playout400.gif		playout400.gif
playout800.gif		playout800.gif
policy_value_net.py		policy_value_net.py
policy_value_net_numpy.py		policy_value_net_numpy.py
policy_value_net_numpy_pytorch.py		policy_value_net_numpy_pytorch.py
policy_value_net_pytorch.py		policy_value_net_pytorch.py
print_figure.py		print_figure.py
print_figure2.py		print_figure2.py
test.py		test.py
train.py		train.py