garage.tf.regressors.regressor module¶
Regressor base classes without Parameterized.
-
class
Regressor
(input_shape, output_dim, name)[source]¶ Bases:
garage.tf.models.module.Module
Regressor base class.
Parameters:
-
class
StochasticRegressor
(input_shape, output_dim, name)[source]¶ Bases:
garage.tf.regressors.regressor.Regressor
,garage.tf.models.module.StochasticModule
StochasticRegressor base class.
-
log_likelihood_sym
(x_var, y_var, name=None)[source]¶ Symbolic graph of the log likelihood.
Parameters: - x_var (tf.Tensor) – Input tf.Tensor for the input data.
- y_var (tf.Tensor) – Input tf.Tensor for the label of data.
- name (str) – Name of the new graph.
Returns: tf.Tensor output of the symbolic log likelihood.
-