garage.np.baselines
¶
Baselines (value functions) which use NumPy as a numerical backend.
-
class
Baseline
¶ Bases:
abc.ABC
Base class for all baselines.
-
class
LinearFeatureBaseline
(env_spec, reg_coeff=1e-05, name='LinearFeatureBaseline')¶ Bases:
garage.np.baselines.baseline.Baseline
A linear value function (baseline) based on features.
Parameters: -
get_param_values
(self)¶ Get parameter values.
Returns: A list of values of each parameter. Return type: List[np.ndarray]
-
set_param_values
(self, flattened_params)¶ Set param values.
Parameters: flattened_params (np.ndarray) – A numpy array of parameter values.
-
-
class
LinearMultiFeatureBaseline
(env_spec, features=None, reg_coeff=1e-05, name='LinearMultiFeatureBaseline')¶ Bases:
garage.np.baselines.LinearFeatureBaseline
A linear value function (baseline) based on features.
Parameters: -
get_param_values
(self)¶ Get parameter values.
Returns: A list of values of each parameter. Return type: List[np.ndarray]
-
set_param_values
(self, flattened_params)¶ Set param values.
Parameters: flattened_params (np.ndarray) – A numpy array of parameter values.
-
-
class
ZeroBaseline
(env_spec)¶ Bases:
garage.np.baselines.baseline.Baseline
Base class for all baselines.
-
get_param_values
(self, **kwargs)¶
-
set_param_values
(self, val, **kwargs)¶
-
fit
(self, paths)¶ Fit regressor based on paths.
Parameters: paths (dict[numpy.ndarray]) – Sample paths.
-
predict
(self, path)¶ Predict value based on paths.
Parameters: paths (dict[numpy.ndarray]) – Sample paths. Returns: Predicted value. Return type: numpy.ndarray
-
predict_n
(self, paths)¶
-