AlphaZero_Gomoku icon indicating copy to clipboard operation
AlphaZero_Gomoku copied to clipboard

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

Results 76 AlphaZero_Gomoku issues
Sort by recently updated
recently updated
newest added

为什么要在'play_data'中反转 input features? play_data 1: ``` [[0,0,0], [0,1,0], [0,0,0]] # white [[0,0,0], [0,0,0], [0,0,0]] # black [[0,0,0], [0,1,0], [0,0,0]] # action [[0,0,0], [0,0,0], [0,0,0]] # player ``` play_data 2: ```...

如题,并且我使用的是Tensorflow,训练中生成了3个文件 best_policy.model.data-00000-of-00001 best_policy.model.index best_policy.model.meta

请各位大佬批评指点

Traceback (most recent call last): File "E:/project/AlphaZero_Gomoku/human_play.py", line 68, in run policy_param = pickle.load(open(model_file, 'rb')) _pickle.UnpicklingError: A load persistent id instruction was encountered, but no persistent_load function was specified. During...

A class at the University of Alabama is using this repository's code as a starting point for an assignment. Many students were having to make these edits manually, so I...

请问若训练因故中断后是从current_policy.model开始训练好还是从零开始好

作者你好,最近有在学习您的代码,使用的是pytorch版的神经网络,在跑代码的时候,发现GPU利用率几乎为0,我电脑是装好pytorch的,我现在在怀疑我电脑环境问题,但是又找不到问题,在其他issue中有看到是因为mcts过程过于复杂,导致cpu的计算速度跟不上GPU的速度,最终使得训练速度很慢,想问想我现在训练时GPU利用率很低是因为cpu计算速度跟不上吗还是我本地环境有问题,感谢您能花时间回复!