d3rlpy.models.optimizers.SGDFactory

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

An alias for SGD optimizer.

from d3rlpy.optimizers import SGDFactory

factory = SGDFactory(weight_decay=1e-4)

Parameters

• momentum – momentum factor.

• dampening – dampening for momentum.

• weight_decay – weight decay (L2 penalty).

• nesterov – flag to enable Nesterov momentum.

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]