need help : KeyError: 'info' KeyError: 'action'

[lalala215]

dear author:

I have met this problem how can I slove it?

rlpyt.projects.qcpo.qcpo_model.py | normalize_observation :  True
rlpyt.projects.qcpo.qcpo_model.py | normalize_observation :  True
rlpyt.projects.qcpo.qcpo_model.py | normalize_observation :  True
D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\samplers\buffer.py:3: UserWarning: The NumPy module was reloaded (imported a second time). This can in some cases result in small but subtle issues and is discouraged.
  import numpy as np
D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\samplers\buffer.py:3: UserWarning: The NumPy module was reloaded (imported a second time). This can in some cases result in small but subtle issues and is discouraged.
  import numpy as np
D:\Anaconda\envs\qcpo1\lib\site-packages\gym-0.15.7-py3.7.egg\gym\logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32
  warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow'))
Process Process-2:
Traceback (most recent call last):
  File "D:\Anaconda\envs\qcpo1\lib\multiprocessing\process.py", line 297, in _bootstrap
    self.run()
  File "D:\Anaconda\envs\qcpo1\lib\multiprocessing\process.py", line 99, in run
    self._target(*self._args, **self._kwargs)
  File "D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\samplers\buffer.py", line 68, in get_example_outputs
    o, r, d, env_info = env.step(a)
  File "D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\envs\gym.py", line 74, in step
    info = info_to_nt(info)
  File "D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\envs\gym.py", line 125, in info_to_nt
    ntc = globals()[name]
KeyError: 'info'
Traceback (most recent call last):
  File "D:/QCPO-master/rlpyt/rlpyt/projects/qcpo/experiments/train_qcpo.py", line 99, in <module>
    runner.train()
  File "D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\projects\qcpo\experiments\minibatch_rl.py", line 35, in train
    n_itr = self.startup()
  File "D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\runners\minibatch_rl.py", line 81, in startup
    world_size=world_size,
  File "D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\samplers\parallel\base.py", line 78, in initialize
    examples = self._build_buffers(env, bootstrap_value)
  File "D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\samplers\parallel\base.py", line 182, in _build_buffers
    agent_shared=True, env_shared=True, subprocess=True)
  File "D:\Anaconda\envs\qcpo1\lib\site-packages\rlpyt\samplers\buffer.py", line 29, in build_samples_buffer
    all_action = buffer_from_example(examples["action"], (T + 1, B), agent_shared)
  File "<string>", line 2, in __getitem__
  File "D:\Anaconda\envs\qcpo1\lib\multiprocessing\managers.py", line 834, in _callmethod
    raise convert_to_error(kind, result)
KeyError: 'action'

Process finished with exit code 1