[RLlib] Examples folder restructuring (Model examples; final part). (#8278)

- This PR completes any previously missing PyTorch Model counterparts to TFModels in examples/models.
- It also makes sure, all example scripts in the rllib/examples folder are tested for both frameworks and learn the given task (this is often currently not checked) using a --as-test flag in connection with a --stop-reward.

rllib/examples/rollout_worker_custom_workflow.py

@@ -13,8 +13,8 @@ import ray
 from ray import tune
 from ray.rllib.evaluation import RolloutWorker
 from ray.rllib.evaluation.metrics import collect_metrics
+from ray.rllib.policy.policy import Policy
 from ray.rllib.policy.sample_batch import SampleBatch
-from ray.rllib.policy.tests.test_policy import TestPolicy
 
 parser = argparse.ArgumentParser()
 parser.add_argument("--gpu", action="store_true")
@@ -23,7 +23,7 @@ parser.add_argument("--num-workers", type=int, default=2)
 parser.add_argument("--num-cpus", type=int, default=0)
 
 
-class CustomPolicy(TestPolicy):
+class CustomPolicy(Policy):
     """Example of a custom policy written from scratch.
 
     You might find it more convenient to extend TF/TorchPolicy instead