d3rlpy.models.optimizers.OptimizerFactory¶

class d3rlpy.models.optimizers.OptimizerFactory(optim_cls, **kwargs)[source]¶

A factory class that creates an optimizer object in a lazy way.

The optimizers in algorithms can be configured through this factory class.

from torch.optim Adam
from d3rlpy.optimizers import OptimizerFactory
from d3rlpy.algos import DQN

factory = OptimizerFactory(Adam, eps=0.001)

dqn = DQN(optim_factory=factory)

Parameters

optim_cls (Union[Type[torch.optim.optimizer.Optimizer], str]) – An optimizer class.
kwargs (Any) – arbitrary keyword-arguments.

Methods

create(params, lr)[source]¶

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)[source]¶

Returns optimizer parameters.

Parameters: deep (bool) – flag to deeply copy the parameters.
Returns: optimizer parameters.
Return type: Dict[str, Any]