junxiaosong / AlphaZero_Gomoku

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
MIT License
3.33k stars 970 forks source link

修改了游戏规则后训练中的问题 #114

Closed AnterCreeper closed 3 years ago

AnterCreeper commented 3 years ago

Traceback (most recent call last): File "C:\Users\wangz\Desktop\uGo\train.py", line 185, in training_pipeline.run() File "C:\Users\wangz\Desktop\uGo\train.py", line 159, in run self.collect_selfplay_data(self.play_batch_size) File "C:\Users\wangz\Desktop\uGo\train.py", line 79, in collect_selfplay_data temp=self.temp) File "C:\Users\wangz\Desktop\uGo\game.py", line 201, in start_self_play return_prob=1) File "C:\Users\wangz\Desktop\uGo\mcts_alphaZero.py", line 190, in get_action acts, probs = self.mcts.get_move_probs(board, temp) File "C:\Users\wangz\Desktop\uGo\mcts_alphaZero.py", line 152, in get_move_probs acts, visits = zip(*act_visits) ValueError: not enough values to unpack (expected 2, got 0) 初学者求教