metarl.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 (metarl.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.
predict(path)[source]

Predict value based on paths.

Parameters:path (dict[numpy.ndarray]) – Sample paths.
Returns:Predicted value.
Return type:numpy.ndarray
set_param_values(flattened_params)[source]

Set param values.

Parameters:flattened_params (np.ndarray) – A numpy array of parameter values.
class LinearFeatureBaseline(env_spec, reg_coeff=1e-05, name='LinearFeatureBaseline')[source]

Bases: metarl.np.baselines.baseline.Baseline

A linear value function (baseline) based on features.

Parameters:
fit(paths)[source]

Fit regressor based on paths.

Parameters:paths (list[dict]) – Sample paths.
get_param_values()[source]

Get parameter values.

Returns:A list of values of each parameter.
Return type:List[np.ndarray]
predict(path)[source]

Predict value based on paths.

Parameters:path (list[dict]) – Sample paths.
Returns:Predicted value.
Return type:numpy.ndarray
set_param_values(flattened_params)[source]

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')[source]

Bases: metarl.np.baselines.linear_feature_baseline.LinearFeatureBaseline

A linear value function (baseline) based on features.

Parameters:
class ZeroBaseline(env_spec)[source]

Bases: metarl.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]
predict(path)[source]

Predict value based on paths.

Parameters:path (dict[numpy.ndarray]) – Sample paths.
Returns:Predicted value.
Return type:numpy.ndarray
predict_n(paths)[source]
set_param_values(val, **kwargs)[source]

Set param values.

Parameters:flattened_params (np.ndarray) – A numpy array of parameter values.