train.py 文件源码

def main():
  """

  :return:
  """
  _visualiser = None
  if C.USE_VISDOM:
    _visualiser = Visdom(C.VISDOM_SERVER)

  _environment = neo.make(C.ENVIRONMENT,
                          connect_to_running=C.CONNECT_TO_RUNNING,
                          logging_directory=C.LOGGING_DIRECTORY,
                          debug_logging=C.USE_LOGGING)
  _environment.seed(C.RANDOM_SEED)

  if type(C.ARCH_PARAMS['input_size']) == str:
    C.ARCH_PARAMS['input_size'] = _environment.observation_space.shape
  print('observation dimensions: ', C.ARCH_PARAMS['input_size'])

  if type(C.ARCH_PARAMS['output_size']) == str:
    C.ARCH_PARAMS['output_size'] = _environment.action_space.n
  print('action dimensions: ', C.ARCH_PARAMS['output_size'])

  _agent = PolicyAgent(C.ARCH_PARAMS['input_size'],C.ARCH_PARAMS['output_size'])

  _trained_model = training_loop(_agent,
                                 _environment)

  _environment.render(close=True)
  _environment.close()

  save_model(_trained_model, C)