garage.torch.optimizers
¶
PyTorch optimizers.
-
class
ConjugateGradientOptimizer
(params, max_constraint_value, cg_iters=10, max_backtracks=15, backtrack_ratio=0.8, hvp_reg_coeff=1e-05, accept_violation=False)¶ Bases:
torch.optim.Optimizer
Performs constrained optimization via backtracking 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
params (iterable) – Iterable of parameters to optimize.
max_constraint_value (float) – Maximum constraint value.
cg_iters (int) – The number of CG iterations used to calculate A^-1 g
max_backtracks (int) – Max number of iterations for backtrack linesearch.
backtrack_ratio (float) – backtrack ratio for backtracking line search.
hvp_reg_coeff (float) – A small value so that A -> A + reg*I. It is used by Hessian Vector Product calculation.
accept_violation (bool) – whether to accept the descent step if it violates the line search condition after exhausting all backtracking budgets.
-
step
(self, f_loss, f_constraint)¶ Take an optimization step.
- Parameters
f_loss (callable) – Function to compute the loss.
f_constraint (callable) – Function to compute the constraint value.
-
property
state
(self)¶ dict: The hyper-parameters of the optimizer.
-
class
DifferentiableSGD
(module, lr=0.001)¶ Differentiable Stochastic Gradient Descent.
DifferentiableSGD performs the same optimization step as SGD, but instead of updating parameters in-place, it saves updated parameters in new tensors, so that the gradient of functions of new parameters can flow back to the pre-updated parameters.
- Parameters
module (torch.nn.module) – A torch module whose parameters needs to be optimized.
lr (float) – Learning rate of stochastic gradient descent.
-
step
(self)¶ Take an optimization step.
-
zero_grad
(self)¶ Sets gradients of all model parameters to zero.
-
class
OptimizerWrapper
(optimizer, module, max_optimization_epochs=1, minibatch_size=None)¶ A wrapper class to handle torch.optim.optimizer.
- Parameters
optimizer (Union[type, tuple[type, dict]]) – Type of optimizer for policy. This can be an optimizer type such as torch.optim.Adam or a tuple of type and dictionary, where dictionary contains arguments to initialize the optimizer. e.g. (torch.optim.Adam, {‘lr’ : 1e-3}) Sample strategy to be used when sampling a new task.
module (torch.nn.Module) – Module to be optimized.
max_optimization_epochs (int) – Maximum number of epochs for update.
minibatch_size (int) – Batch size for optimization.
-
get_minibatch
(self, *inputs)¶ Yields a batch of inputs.
Notes: P is the size of minibatch (self._minibatch_size)
- Parameters
*inputs (list[torch.Tensor]) – A list of inputs. Each input has shape \((N \dot [T], *)\).
- Yields
list[torch.Tensor] –
- A list batch of inputs. Each batch has shape
\((P, *)\).
-
zero_grad
(self)¶ Clears the gradients of all optimized
torch.Tensor
s.
-
step
(self, **closure)¶ Performs a single optimization step.
- Parameters
**closure (callable, optional) – A closure that reevaluates the model and returns the loss.