garage.torch.policies.stochastic_policy module¶
Base Stochastic Policy.
-
class
StochasticPolicy
(env_spec, name)[source]¶ Bases:
garage.torch.policies.policy.Policy
,abc.ABC
Abstract base class for torch stochastic policies.
-
forward
(observations)[source]¶ Compute the action distributions from the observations.
Parameters: observations (torch.Tensor) – Batch of observations on default torch device. Returns: Batch distribution of actions. dict[str, torch.Tensor]: Additional agent_info, as torch Tensors. Do not need to be detached, and can be on any device.Return type: torch.distributions.Distribution
-
get_action
(observation)[source]¶ Get a single action given an observation.
Parameters: observation (np.ndarray) – Observation from the environment. Shape is \(env_spec.observation_space\). Returns: - np.ndarray: Predicted action. Shape is
- \(env_spec.action_space\).
- dict:
- np.ndarray[float]: Mean of the distribution
- np.ndarray[float]: Standard deviation of logarithmic
- values of the distribution.
Return type: tuple
-
get_actions
(observations)[source]¶ Get actions given observations.
Parameters: observations (np.ndarray) – Observations from the environment. Shape is \(batch_dim \bullet env_spec.observation_space\). Returns: - np.ndarray: Predicted actions.
- \(batch_dim \bullet env_spec.action_space\).
- dict:
- np.ndarray[float]: Mean of the distribution.
- np.ndarray[float]: Standard deviation of logarithmic
- values of the distribution.
Return type: tuple
-