DeepReinforcementLearning：用于在Python中进行深度强化学习的AlphaZero方法的副本
需积分: 0 74 浏览量
2021-02-27
05:51:49
上传
评论
收藏 272KB ZIP 举报
DeepReinforcementLearning-master.zip （40个子文件） 
DeepReinforcementLearning-master 
loss.py 363B agent.py 6KB main.py 6KB utils.py 383B game.py 6KB loggers.py 943B LICENSE 34KB .DS_Store 18KB settings.py 59B
requirements.txt 755B memory.py 698B model.py 6KB run.ipynb 76KB .gitignore 1KB MCTS.py 3KB run models .DS_Store 6KB .gitignore 0B logs .DS_Store 6KB .gitignore 0B memory .DS_Store 6KB .gitignore 0B .DS_Store 14KB config.py 622B config.py 622B funcs.py 6KB .ipynb_checkpoints notebook-checkpoint.ipynb 376KB test2-Copy1-checkpoint.ipynb 548KB run-checkpoint.ipynb 10KB create_data-checkpoint.ipynb 72B live-checkpoint.ipynb 114KB check_model-checkpoint.ipynb 37KB loss checking-checkpoint.ipynb 4KB live-MetaSquares-checkpoint.ipynb 118KB README.md 229B initialise.py 86B games connect4 game.py 6KB .DS_Store 6KB .DS_Store 8KB metasquares game.py 8KB .DS_Store 6KB资源评论
