garage.np.baselines
¶
Baselines (value functions) which use NumPy as a numerical backend.
- class Baseline[source]¶
Bases:
abc.ABC
Base class for all baselines.
- 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
- 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.LinearFeatureBaseline
A linear value function (baseline) based on features.
- Parameters
- get_param_values()¶
Get parameter values.
- Returns
A list of values of each parameter.
- Return type
List[np.ndarray]
- set_param_values(flattened_params)¶
Set param values.
- Parameters
flattened_params (np.ndarray) – A numpy array of parameter values.
- class ZeroBaseline(env_spec)[source]¶
Bases:
garage.np.baselines.baseline.Baseline
Base class for all baselines.
- fit(paths)[source]¶
Fit regressor based on paths.
- Parameters
paths (dict[numpy.ndarray]) – Sample paths.