代理商培训期间出现BrokenPipeError

Question

我使用Unity的ML-Agents库将代理添加到我的游戏中。当我从Anaconda提示符开始训练时，一开始看起来一切都很好，但是随后，我收到了BrokenPipeError的消息，训练停止了。我搜索了，找不到任何解决方案。我尝试禁用防火墙，因为有人建议使用它，但它不起作用。

错误是：

Traceback (most recent call last):
  File "C:\Users\user\anaconda3\envs\mlagentsrelease1\lib\multiprocessing\connection.py", line 312, in _recv_bytes
    nread, err = ov.GetOverlappedResult(True)
BrokenPipeError: [WinError 109] Boru sonlandı

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\user\anaconda3\envs\mlagentsrelease1\lib\multiprocessing\process.py", line 297, in _bootstrap
    self.run()
  File "C:\Users\user\anaconda3\envs\mlagentsrelease1\lib\multiprocessing\process.py", line 99, in run
    self._target(*self._args, **self._kwargs)
  File "c:\users\user\desktop\ml-agents-15.0-capstone\ml-agents-release_1\ml-agents\mlagents\trainers\subprocess_env_manager.py", line 151, in worker
    req: EnvironmentRequest = parent_conn.recv()
  File "C:\Users\user\anaconda3\envs\mlagentsrelease1\lib\multiprocessing\connection.py", line 250, in recv
    buf = self._recv_bytes()
  File "C:\Users\user\anaconda3\envs\mlagentsrelease1\lib\multiprocessing\connection.py", line 321, in _recv_bytes
    raise EOFError
EOFError