metarl.tf.policies.uniform_control_policy module¶

Uniform control policy.

class UniformControlPolicy(env_spec)[source]¶

Policy that output random action uniformly.

Parameters:	env_spec (metarl.envs.env_spec.EnvSpec) – Environment specification.

get_action(observation)[source]¶

Get single action from this policy for the input observation.

Parameters:	observation (numpy.ndarray) – Observation from environment.
Returns:	Action dict: Predicted action and agent information. It returns an empty dict since there is no parameterization.
Return type:	numpy.ndarray

get_actions(observations)[source]¶

Get multiple actions from this policy for the input observations.

Parameters:	observations (numpy.ndarray) – Observations from environment.
Returns:	Actions dict: Predicted action and agent information. It returns an empty dict since there is no parameterization.
Return type:	numpy.ndarray

vectorized¶

Vectorized or not.

Returns:	True if primitive supports vectorized operations.
Return type:	Bool