Unable to load multiprocessing context for my validated custom gym environment.

[Yash271100]

This is the code I am implementing: -
Along with other dependencies;
from tf_agents.environments import ParallelPyEnvironment

num_cpu = 4;
def GetmyENV():
      return PyENV
parallel_py_env = ParallelPyEnvironment([GetmyENV]*int(num_cpu))

The RuntimeError I get is

RuntimeError: Unable to load multiprocessing context.

Please ensure that you properly initialize your program by wrapping your main()
call:

def main(argv):
  ...

if __name__ == '__main__':
  tf_agents.system.multiprocessing.handle_main(main, extra_state_savers=...)

or, if using absl.app:

if __name__ == '__main__':
  tf_agents.system.multiprocessing.handle_main(
      functools.partial(absl.app.run, main), extra_state_savers=...)


For unit tests, this also means wrapping your test.main using handle_test_main:

if __name__ == '__main__':
  tf_agents.system.multiprocessing.handle_test_main(
      tf.test.main, extra_state_savers=...)

or

if __name__ == '__main__':
  tf_agents.system.multiprocessing.handle_test_main(
      tf_agents.utils.test_utils.main, extra_state_savers=...)

If you are in interactive mode (e.g. python console, ipython, jupyter notebook)
use:

tf_agents.system.multiprocessing.enable_interactive_mode(
    extra_state_savers=...)

For more details on state savers, see the docstrings for
`tf_agents.multiprocessing.handle_*` and:

https://pythonspeed.com/articles/python-multiprocessing/

  In call to configurable 'ParallelPyEnvironment' (<class 'tf_agents.environments.parallel_py_environment.ParallelPyEnvironment'>)

I do think my PyEnvironment does not have any issues as the validation was successful. However, my initialization might be incorrect. Kindly help me with this.

[Yash271100]

I get the same error using the standard CardGameEnv() explained in the tutorial provided by Tensorflow.