garage.tf.optimizers.first_order_optimizer module

First order optimizer.

class FirstOrderOptimizer(optimizer=None, learning_rate=None, max_epochs=1000, tolerance=1e-06, batch_size=32, callback=None, verbose=False, name='FirstOrderOptimizer')

Bases: object

First order optimier.

Performs (stochastic) gradient descent, possibly using fancier methods like ADAM etc.

Parameters:

• optimizer (tf.Optimizer) – Optimizer to be used.
• learning_rate (dict) – learning rate arguments. learning rates are our main interest parameters to tune optimizers.
• max_epochs (int) – Maximum number of epochs for update.
• tolerance (float) – Tolerance for difference in loss during update.
• batch_size (int) – Batch size for optimization.
• callback (callable) – Function to call during each epoch. Default is None.
• verbose (bool) – If true, intermediate log message will be printed.
• name (str) – Name scope of the optimizer.

loss(inputs, extra_inputs=None)

The loss.

Parameters:

• inputs (list[numpy.ndarray]) – List of input values.
• extra_inputs (list[numpy.ndarray]) – List of extra input values.

Returns:

Loss.

Return type:

float

Raises:

Exception – If loss function is None, i.e. not defined.

optimize(inputs, extra_inputs=None, callback=None)

Perform optimization.

Parameters:

• inputs (list[numpy.ndarray]) – List of input values.
• extra_inputs (list[numpy.ndarray]) – List of extra input values.
• callback (callable) – Function to call during each epoch. Default is None.

Raises:

• NotImplementedError – If inputs are invalid.
• Exception – If loss function is None, i.e. not defined.

update_opt(loss, target, inputs, extra_inputs=None, **kwargs)

Construct operation graph for the optimizer.

Parameters:

• loss (tf.Tensor) – Loss objective to minimize.
• target (object) – Target object to optimize. The object should implemenet get_params() and get_param_values.
• inputs (list[tf.Tensor]) – List of input placeholders.
• extra_inputs (list[tf.Tensor]) – List of extra input placeholders.
• kwargs (dict) – Extra unused keyword arguments. Some optimizers have extra input, e.g. KL constraint.