Example 4-5. ValueError: Cannot evaluate w/o an evaluation worker set in the Trainer or w/o an env on the local worker! about learning_ray HOT 3 CLOSED

In [252]: checkpoint = trainer.save()
     ...: print(checkpoint)
     ...:
     ...: evaluation = trainer.evaluate(checkpoint)
     ...: print(pretty_print(evaluation))
     ...:
     ...: restored_trainer = DQNTrainer(env=GymEnvironment)
     ...: restored_trainer.restore(checkpoint)
/root/ray_results/DQN_GymEnvironment_2022-10-25_10-50-33_uvb3xkn/checkpoint_000010
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Input In [252], in <cell line: 4>()
      1 checkpoint = trainer.save()
      2 print(checkpoint)
----> 4 evaluation = trainer.evaluate(checkpoint)
      5 print(pretty_print(evaluation))
      7 restored_trainer = DQNTrainer(env=GymEnvironment)

File ~/.cache/pypoetry/virtualenvs/ray-KeD1w6JO-py3.9/lib/python3.9/site-packages/ray/rllib/algorithms/algorithm.py:775, in Algorithm.evaluate(self, duration_fn)
    770 else:
    771     if (
    772         self.evaluation_workers is None
    773         and self.workers.local_worker().input_reader is None
    774     ):
--> 775         raise ValueError(
    776             "Cannot evaluate w/o an evaluation worker set in "
    777             "the Trainer or w/o an env on the local worker!\n"
    778             "Try one of the following:\n1) Set "
    779             "`evaluation_interval` >= 0 to force creating a "
    780             "separate evaluation worker set.\n2) Set "
    781             "`create_env_on_driver=True` to force the local "
    782             "(non-eval) worker to have an environment to "
    783             "evaluate on."
    784         )
    786     # How many episodes/timesteps do we need to run?
    787     # In "auto" mode (only for parallel eval + training): Run as long
    788     # as training lasts.
    789     unit = self.config["evaluation_duration_unit"]

Input In [252], in <cell line: 4>()
      1 checkpoint = trainer.save()
      2 print(checkpoint)
----> 4 evaluation = trainer.evaluate(checkpoint)
      5 print(pretty_print(evaluation))
      7 restored_trainer = DQNTrainer(env=GymEnvironment)

File ~/.cache/pypoetry/virtualenvs/ray-KeD1w6JO-py3.9/lib/python3.9/site-packages/ray/rllib/algorithms/algorithm.py:775, in Algorithm.evaluate(self, duration_fn)
    770 else:
    771     if (
    772         self.evaluation_workers is None
    773         and self.workers.local_worker().input_reader is None
    774     ):
--> 775         raise ValueError(
    776             "Cannot evaluate w/o an evaluation worker set in "
    777             "the Trainer or w/o an env on the local worker!\n"
    778             "Try one of the following:\n1) Set "
    779             "`evaluation_interval` >= 0 to force creating a "
    780             "separate evaluation worker set.\n2) Set "
    781             "`create_env_on_driver=True` to force the local "
    782             "(non-eval) worker to have an environment to "
    783             "evaluate on."
    784         )
    786     # How many episodes/timesteps do we need to run?
    787     # In "auto" mode (only for parallel eval + training): Run as long
    788     # as training lasts.
    789     unit = self.config["evaluation_duration_unit"]

ValueError: Cannot evaluate w/o an evaluation worker set in the Trainer or w/o an env on the local worker!
Try one of the following:
1) Set `evaluation_interval` >= 0 to force creating a separate evaluation worker set.
2) Set `create_env_on_driver=True` to force the local (non-eval) worker to have an environment to evaluate on.