OptimizerHook

class torchrl.trainers.OptimizerHook(optimizer: optim.Optimizer, loss_components: Sequence[str] | None = None)

为一或多个损失组件添加优化器。

参数:

• optimizer (optim.Optimizer) – 应用于 loss_components 的优化器。

• loss_components (Sequence[str], optional) – 损失 TensorDict 中用于对相应值应用优化器的键。如果省略，则优化器将应用于所有名称以 loss_ 开头的组件。

示例

>>> optimizer_hook = OptimizerHook(optimizer, ["loss_actor"])
>>> trainer.register_op("optimizer", optimizer_hook)

register(trainer, name='optimizer') → None

Registers the hook in the trainer at a default location.

参数:

• trainer (Trainer) – the trainer where the hook must be registered.

• name (str) – the name of the hook.

注意

To register the hook at another location than the default, use register_op().