bolero.environment.ContextualEnvironment¶

class bolero.environment.ContextualEnvironment[source]¶

Common interface for (contextual) environments.

__init__()¶

x.__init__(…) initializes x; see help(type(x)) for signature

get_args()¶

Get parameters for this estimator.

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

get_feedback()¶

Get the feedbacks for the last evaluation period.

Returns:	feedbacks : array Feedback values

get_maximum_feedback(context)[source]¶

Returns the maximum sum of feedbacks obtainable in given context.

get_num_context_dims()[source]¶

Returns the number of context dimensions.

get_num_inputs()¶

Get number of environment inputs.

Parameters:	n_inputs : int Number of environment inputs

get_num_outputs()¶

Get number of environment outputs.

Parameters:	n_outputs : int Number of environment outputs

get_outputs(values)¶

Get environment outputs, e.g. state of the environment.

Parameters:	values : array Outputs of the environment, will be modified

init()¶

Initialize environment.

is_behavior_learning_done()¶

Check if the behavior learning is finished.

Returns:	finished : bool Is the learning of a behavior finished?

is_evaluation_done()¶

Check if the evaluation of the behavior is finished.

Returns:	finished : bool Is the evaluation finished?

request_context(context)[source]¶

Request that a specific context is used.

Parameters:	context : array-like, shape (n_context_dims,) The requested context that shall be used in the next rollout. Defaults to None. In that case, the environment selects the next context
Returns:	context : array-like, shape (n_context_dims,) The actual context used in the next rollout. This may or may not be the requested context, depending on the respective environment.

reset()¶

Reset state of the environment.

set_inputs(values)¶

Set environment inputs, e.g. next action.

Parameters:	values : array, Input of the environment

step_action()¶

Take a step in the environment.