bolero.controller.ContextualController¶

class bolero.controller.ContextualController(config={}, environment=None, behavior_search=None, **kwargs)[source]¶

Controller for contextual problems.

See base class “Controller” for details on usage.

The controller subsection of the configuration dictionary may contain the following additional parameters:

• test_contexts (array-like) - the upper-level policy will be evaluated in these contexts

__init__(config={}, environment=None, behavior_search=None, **kwargs)[source]¶

episode_with(behavior, meta_parameter_keys=[], meta_parameters=[], record=True)¶

Execute a behavior in the environment.

Parameters:	behavior : Behavior Fix behavior meta_parameter_keys : list, optional (default: []) Meta parameter keys meta_parameters : list, optional (default: []) Meta parameter values record : bool, optional (default: True) Record feedbacks or trajectories if activated
Returns:	feedbacks : array, shape (n_steps,) Feedback for each step in the environment

get_args()¶

Get parameters for this estimator.

Returns:	params : mapping of string to any Parameter names mapped to their values.

learn(meta_parameter_keys=(), meta_parameters=())¶

Learn the behavior.

Parameters:	meta_parameter_keys : list Meta parameter keys meta_parameters : list Meta parameter values
Returns:	feedback_history : array, shape (n_episodes or less, dim_feedback) Feedbacks for each episode. If is_behavior_learning_done is True before the n_episodes is reached, the length of feedback_history is shorter than n_episodes.

trajectories_¶

inputs to the environment (outputs of the behavior)