:py:mod:`rofunc.learning.RofuncRL.processors.schedulers`
========================================================

.. py:module:: rofunc.learning.RofuncRL.processors.schedulers

.. autodoc2-docstring:: rofunc.learning.RofuncRL.processors.schedulers
   :allowtitles:

Module Contents
---------------

Classes
~~~~~~~

.. list-table::
   :class: autosummary longtable
   :align: left

   * - :py:obj:`KLAdaptiveRL <rofunc.learning.RofuncRL.processors.schedulers.KLAdaptiveRL>`
     - .. autodoc2-docstring:: rofunc.learning.RofuncRL.processors.schedulers.KLAdaptiveRL
          :summary:

API
~~~

.. py:class:: KLAdaptiveRL(optimizer: torch.optim.Optimizer, kl_threshold: float = 0.008, min_lr: float = 1e-06, max_lr: float = 0.01, kl_factor: float = 2, lr_factor: float = 1.5, last_epoch: int = -1, verbose: bool = False)
   :canonical: rofunc.learning.RofuncRL.processors.schedulers.KLAdaptiveRL

   Bases: :py:obj:`torch.optim.lr_scheduler._LRScheduler`

   .. autodoc2-docstring:: rofunc.learning.RofuncRL.processors.schedulers.KLAdaptiveRL

   .. rubric:: Initialization

   .. autodoc2-docstring:: rofunc.learning.RofuncRL.processors.schedulers.KLAdaptiveRL.__init__

   .. py:method:: step(kl: typing.Optional[typing.Union[torch.Tensor, float]] = None, epoch: typing.Optional[int] = None) -> None
      :canonical: rofunc.learning.RofuncRL.processors.schedulers.KLAdaptiveRL.step

      .. autodoc2-docstring:: rofunc.learning.RofuncRL.processors.schedulers.KLAdaptiveRL.step