garage.np.baselines package¶
Baselines (value functions) which use NumPy as a numerical backend.
-
class
Baseline
(env_spec)[source]¶ Bases:
abc.ABC
Base class for all baselines.
Parameters: env_spec (garage.envs.env_spec.EnvSpec) – Environment specification. -
fit
(paths)[source]¶ Fit regressor based on paths.
Parameters: paths (dict[numpy.ndarray]) – Sample paths.
-
get_param_values
()[source]¶ Get parameter values.
Returns: A list of values of each parameter. Return type: List[np.ndarray]
-
log_diagnostics
(paths)[source]¶ Log diagnostic information.
Parameters: paths (list[dict]) – A list of collected paths.
-
-
class
LinearFeatureBaseline
(env_spec, reg_coeff=1e-05, name='LinearFeatureBaseline')[source]¶ Bases:
garage.np.baselines.baseline.Baseline
A linear value function (baseline) based on features.
Parameters: - env_spec (garage.envs.env_spec.EnvSpec) – Environment specification.
- reg_coeff (float) – Regularization coefficient.
- name (str) – Name of baseline.
-
get_param_values
()[source]¶ Get parameter values.
Returns: A list of values of each parameter. Return type: List[np.ndarray]
-
class
LinearMultiFeatureBaseline
(env_spec, features=None, reg_coeff=1e-05, name='LinearMultiFeatureBaseline')[source]¶ Bases:
garage.np.baselines.linear_feature_baseline.LinearFeatureBaseline
A linear value function (baseline) based on features.
Parameters: - env_spec (garage.envs.env_spec.EnvSpec) – Environment specification.
- reg_coeff (float) – Regularization coefficient.
- features (list[str]) – Name of features.
- name (str) – Name of baseline.
-
class
ZeroBaseline
(env_spec)[source]¶ Bases:
garage.np.baselines.baseline.Baseline
-
fit
(paths)[source]¶ Fit regressor based on paths.
Parameters: paths (dict[numpy.ndarray]) – Sample paths.
-
get_param_values
(**kwargs)[source]¶ Get parameter values.
Returns: A list of values of each parameter. Return type: List[np.ndarray]
-