d3rlpy.models.optimizers.SGDFactory

class d3rlpy.models.optimizers.SGDFactory(momentum=0, dampening=0, weight_decay=0, nesterov=False, **kwargs)[source]

An alias for SGD optimizer.

from d3rlpy.optimizers import SGDFactory

factory = SGDFactory(weight_decay=1e-4)
Parameters

  • momentum (float) – momentum factor.

  • dampening (float) – dampening for momentum.

  • weight_decay (float) – weight decay (L2 penalty).

  • nesterov (bool) – flag to enable Nesterov momentum.

  • kwargs (Any) –

Methods

create(params, lr)

Returns an optimizer object.

Parameters

  • params (list) – a list of PyTorch parameters.

  • lr (float) – learning rate.

Returns

an optimizer object.

Return type

torch.optim.Optimizer

get_params(deep=False)

Returns optimizer parameters.

Parameters

deep (bool) – flag to deeply copy the parameters.

Returns

optimizer parameters.

Return type

Dict[str, Any]