:py:mod:`fragile.optimize.evotorch`
===================================

.. py:module:: fragile.optimize.evotorch

.. autoapi-nested-parse::

   This modes implements an interfacing with the `evotorch` library.



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

Classes
~~~~~~~

.. autoapisummary::

   fragile.optimize.evotorch.EvotorchEnv




.. py:class:: EvotorchEnv(algorithm, function = None, bounds = None, **kwargs)

   Bases: :py:obj:`fragile.core.env.Function`

   This environment implements an interface with the `evotorch` library.

   When providing an instance of an evotorch :class:`Searcher` it will     wrap it and allow to use all the fragile features on top of evotorch, such as     plotting, custom policies, etc.

   .. py:attribute:: default_inputs
      

      

   .. py:attribute:: default_outputs
      :annotation: = ['observs', 'rewards', 'oobs']

      

   .. py:method:: algorithm()
      :property:

      Return the evotorch :class:`SearchAlgorithm` instance used by this environment.


   .. py:method:: population()
      :property:

      Access the :class:`SolutionBatch` instance used by the evotorch :class:`SearchAlgorithm`.


   .. py:method:: problem()
      :property:

      Access the :class:`Problem` instance used by the evotorch :class:`SearchAlgorithm`.


   .. py:method:: dtype()
      :property:

      Access the dtype used by the evotorch :class:`SearchAlgorithm` for the solution values.


   .. py:method:: eval_dtype()
      :property:

      Access the dtype used by the :class:`SearchAlgorithm` for the solution evaluations.


   .. py:method:: solution_length()
      :property:

      Access the length of the solution used by the evotorch :class:`SearchAlgorithm`.


   .. py:method:: _get_bounds()

      Initialize the :class:`Bounds` instance used by this environment.

      Extract all the information about the dimensionality and data type of the solutions
      from the problem instance used by the evotorch :class:`SearchAlgorithm`.


   .. py:method:: _get_function()

      Return a function that sets the values of the evotorch :class:`SolutionBatch`         with the provided points and iterates the evotorch :class:`SearchAlgorithm`         to obtain new solutions.


   .. py:method:: step(actions, observs, **kwargs)

      Sum the target action to the observations to obtain the new points, and         evaluate the reward and boundary conditions.

      :returns:

                Dictionary containing the information of the new points evaluated.

                 ``{"observs": new_points, "rewards": scalar array,              "oobs": boolean array}``


   .. py:method:: reset(inplace = True, root_walker = None, states = None, **kwargs)

      Reset the :class:`Function` to the start of a new episode and updates its internal data.