BrokenPipeError and EOFError while training

The training process was running fine and suddenly it throws these errors. The first few episodes are fine.
I used this command from Anaconda Prompt, using with a virtual env:
mlagents-learn trainer_config.yaml --env=UnityProject.exe --run-id=1 --train.

Here is my log:

2020-04-18 07:53:22 INFO [trainer.py:214] 2: Brain: Step: 110000. Time Elapsed: 6598.126 s Mean Reward: 1.000. Std of Reward: 0.000. Training.
(UnityMLAVnv) (base) C:\Users\User\Desktop>Process Process-1:
Traceback (most recent call last):
File "c:\programdata\anaconda3\lib\multiprocessing\connection.py", line 312, in _recv_bytes
nread, err = ov.GetOverlappedResult(True)
BrokenPipeError: [WinError 109] パイプは終了しました。
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "c:\programdata\anaconda3\lib\multiprocessing\process.py", line 297, in _bootstrap
self.run()
File "c:\programdata\anaconda3\lib\multiprocessing\process.py", line 99, in run
self._target(*self._args, **self._kwargs)
File "c:\users\user\unitymlavnv\lib\site-packages\mlagents\trainers\subprocess_env_manager.py", line 120, in worker
cmd: EnvironmentCommand = parent_conn.recv()
File "c:\programdata\anaconda3\lib\multiprocessing\connection.py", line 250, in recv
buf = self._recv_bytes()
File "c:\programdata\anaconda3\lib\multiprocessing\connection.py", line 321, in _recv_bytes
raise EOFError​

EOFError
Environment:
- OS: Windows 10
- _ML-Agents 0.15.1
- _TensorFlow 2.0.1

 

I have the same isssue, have you figured out how to solve this? Thx!