# <ray.rllib.models.preprocessors.GenericPixelPreprocessor object at 0x7fc4d049de80>
# Observations should be preprocessed prior to feeding into a model
env.reset().shape
# (210, 160, 3)
prep.transform(env.reset()).shape
# (84, 84, 3)
# __preprocessing_observations_end__
# __query_action_dist_start__
# Get a reference to the policy
import numpy as np
from ray.rllib.algorithms.ppo import PPO
algo = PPO(env="CartPole-v0", config={"framework": "tf2", "num_workers": 0})
policy = algo.get_policy()
# <ray.rllib.policy.eager_tf_policy.PPOTFPolicy_eager object at 0x7fd020165470>
# Run a forward pass to get model output logits. Note that complex observations
# must be preprocessed as in the above code block.
logits, _ = policy.model({"obs": np.array([[0.1, 0.2, 0.3, 0.4]])})
# (<tf.Tensor: id=1274, shape=(1, 2), dtype=float32, numpy=...>, [])
# Compute action distribution given logits
policy.dist_class
# <class_object 'ray.rllib.models.tf.tf_action_dist.Categorical'>
dist = policy.dist_class(logits, policy.model)
# <ray.rllib.models.tf.tf_action_dist.Categorical object at 0x7fd02301d710>
# Query the distribution for samples, sample logps
dist.sample()
# <ray.rllib.models.preprocessors.GenericPixelPreprocessor object at 0x7fc4d049de80>
# Observations should be preprocessed prior to feeding into a model
env.reset().shape
# (210, 160, 3)
prep.transform(env.reset()).shape
# (84, 84, 3)
# __preprocessing_observations_end__
# __query_action_dist_start__
# Get a reference to the policy
import numpy as np
from ray.rllib.algorithms.ppo import PPO
trainer = PPO(env="CartPole-v0", config={"framework": "tf2", "num_workers": 0})
policy = trainer.get_policy()
# <ray.rllib.policy.eager_tf_policy.PPOTFPolicy_eager object at 0x7fd020165470>
# Run a forward pass to get model output logits. Note that complex observations
# must be preprocessed as in the above code block.
logits, _ = policy.model({"obs": np.array([[0.1, 0.2, 0.3, 0.4]])})
# (<tf.Tensor: id=1274, shape=(1, 2), dtype=float32, numpy=...>, [])
# Compute action distribution given logits
policy.dist_class
# <class_object 'ray.rllib.models.tf.tf_action_dist.Categorical'>
dist = policy.dist_class(logits, policy.model)
# <ray.rllib.models.tf.tf_action_dist.Categorical object at 0x7fd02301d710>
# Query the distribution for samples, sample logps
dist.sample()