garage.tf.optimizers package

class ConjugateGradientOptimizer(cg_iters=10, reg_coeff=1e-05, subsample_factor=1.0, backtrack_ratio=0.8, max_backtracks=15, accept_violation=False, hvp_approach=None, num_slices=1)

Bases: object

Performs constrained optimization via line search.

The search direction is computed using a conjugate gradient algorithm, which gives x = A^{-1}g, where A is a second order approximation of the constraint and g is the gradient of the loss function.

Parameters:

• cg_iters (int) – The number of CG iterations used to calculate A^-1 g
• reg_coeff (float) – A small value so that A -> A + reg*I
• subsample_factor (float) – Subsampling factor to reduce samples when using “conjugate gradient. Since the computation time for the descent direction dominates, this can greatly reduce the overall computation time.
• backtrack_ratio (float) – backtrack ratio for backtracking line search.
• max_backtracks (int) – Max number of iterations for backtrack linesearch.
• accept_violation (bool) – whether to accept the descent step if it violates the line search condition after exhausting all backtracking budgets.
• hvp_approach (HessianVectorProduct) – A class that computes Hessian-vector products.
• num_slices (int) – Hessian-vector product function’s inputs will be divided into num_slices and then averaged together to improve performance.

constraint_val(inputs, extra_inputs=None)

Constraint value.

Parameters:

• inputs (list[numpy.ndarray]) – A list inputs, which could be subsampled if needed. It is assumed that the first dimension of these inputs should correspond to the number of data points
• extra_inputs (list[numpy.ndarray]) – A list of extra inputs which should not be subsampled.

Returns:

Constraint value.

Return type:

float

loss(inputs, extra_inputs=None)

Compute the loss value.

Parameters:

• inputs (list[numpy.ndarray]) – A list inputs, which could be subsampled if needed. It is assumed that the first dimension of these inputs should correspond to the number of data points
• extra_inputs (list[numpy.ndarray]) – A list of extra inputs which should not be subsampled.

Returns:

Loss value.

Return type:

float

optimize(inputs, extra_inputs=None, subsample_grouped_inputs=None, name=None)

Optimize the function.

Parameters:

• inputs (list[numpy.ndarray]) – A list inputs, which could be subsampled if needed. It is assumed that the first dimension of these inputs should correspond to the number of data points
• extra_inputs (list[numpy.ndarray]) – A list of extra inputs which should not be subsampled.
• subsample_grouped_inputs (list[numpy.ndarray]) – Subsampled inputs to be used when subsample_factor is less than one.
• name (str) – The name argument for tf.name_scope.

update_opt(loss, target, leq_constraint, inputs, extra_inputs=None, name=None, constraint_name='constraint')

Update the optimizer.

Build the functions for computing loss, gradient, and the constraint value.

Parameters:

• loss (tf.Tensor) – Symbolic expression for the loss function.
• target (garage.tf.policies.Policy) – A parameterized object to optimize over.
• leq_constraint (tuple[tf.Tensor, float]) – A constraint provided as a tuple (f, epsilon), of the form f(*inputs) <= epsilon.
• inputs (list(tf.Tenosr)) – A list of symbolic variables as inputs, which could be subsampled if needed. It is assumed that the first dimension of these inputs should correspond to the number of data points.
• extra_inputs (list[tf.Tenosr]) – A list of symbolic variables as extra inputs which should not be subsampled.
• name (str) – Name to be passed to tf.name_scope.
• constraint_name (str) – A constraint name for prupose of logging and variable names.

class FiniteDifferenceHvp(base_eps=1e-08, symmetric=True, num_slices=1)

Bases: garage.tf.optimizers.conjugate_gradient_optimizer.HessianVectorProduct

Computes Hessian-vector product using finite difference method.

Parameters:

• base_eps (float) – Base epsilon value.
• symmetric (bool) – Symmetric or not.
• num_slices (int) – Hessian-vector product function’s inputs will be divided into num_slices and then averaged together to improve performance.

update_hvp(f, target, inputs, reg_coeff, name=None)

Build the symbolic graph to compute the Hessian-vector product.

Parameters:

• f (tf.Tensor) – The function whose Hessian needs to be computed.
• target (garage.tf.policies.Policy) – A parameterized object to optimize over.
• inputs (tuple[tf.Tensor]) – The inputs for function f.
• reg_coeff (float) – A small value so that A -> A + reg*I.
• name (str) – Name to be used in tf.name_scope.

class FirstOrderOptimizer(tf_optimizer_cls=None, tf_optimizer_args=None, max_epochs=1000, tolerance=1e-06, batch_size=32, callback=None, verbose=False, name='FirstOrderOptimizer', **kwargs)

Bases: object

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

loss(inputs, extra_inputs=None)

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

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

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.

class LbfgsOptimizer(max_opt_itr=20, callback=None)

Bases: object

Performs unconstrained optimization via L-BFGS.

loss(inputs, extra_inputs=None)

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

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

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.

class PenaltyLbfgsOptimizer(max_opt_itr=20, initial_penalty=1.0, min_penalty=0.01, max_penalty=1000000.0, increase_penalty_factor=2, decrease_penalty_factor=0.5, max_penalty_itr=10, adapt_penalty=True)

Bases: object

Performs constrained optimization via penalized L-BFGS. The penalty term is adaptively adjusted to make sure that the constraint is satisfied.

constraint_val(inputs)

loss(inputs)

optimize(inputs, name=None)

update_opt(loss, target, leq_constraint, inputs, constraint_name='constraint', name=None, *args, **kwargs)

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.
• leq_constraint – A constraint provided as a tuple (f, epsilon), of the form f(*inputs) <= epsilon.
• inputs – A list of symbolic variables as inputs

Returns:

No return value.

Submodules

• garage.tf.optimizers.conjugate_gradient_optimizer module
• garage.tf.optimizers.first_order_optimizer module
• garage.tf.optimizers.lbfgs_optimizer module
• garage.tf.optimizers.penalty_lbfgs_optimizer module
• garage.tf.optimizers.utils module