garage.tf.optimizers.lbfgs_optimizer module

class LbfgsOptimizer(max_opt_itr=20, callback=None)[source]

Bases: object

Performs unconstrained optimization via L-BFGS.

loss(inputs, extra_inputs=None)[source]
optimize(inputs, extra_inputs=None, name=None)[source]
update_opt(loss, target, inputs, extra_inputs=None, name=None, *args, **kwargs)[source]
Parameters:
  • loss – Symbolic expression for the loss function.
  • target – A parameterized object to optimize over. It should implement methods of the

garage.core.paramerized.Parameterized class. :param leq_constraint: A constraint provided as a tuple (f, epsilon),

of the form f(*inputs) <= epsilon.
Parameters:inputs – A list of symbolic variables as inputs
Returns:No return value.