gflownet.proxy.toy
==================

.. py:module:: gflownet.proxy.toy

.. autoapi-nested-parse::

   Reward for the Toy environment.

   The class allows for the assignment of proxy values for each state independently.

   Arbitrarily, the default values are approximately equal to the number of particles
   reaching the final states in Figure 2 of the GFlowNet Foundations paper.



Classes
-------

.. autoapisummary::

   gflownet.proxy.toy.ToyScorer


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

.. py:class:: ToyScorer(values = {3: 30, 4: 14, 6: 23, 8: 10, 9: 30, 10: 5}, **kwargs)

   Bases: :py:obj:`gflownet.proxy.base.Proxy`


   :param values: The proxy values for each state. The keys are the indidices of each state
                  and the values are the proxy values assigned to them.
   :type values: dict


   .. py:attribute:: values_dict


   .. py:method:: setup(env=None)

      Builds a tensor of scores for each state of the environment.

      :param env: An instance of the Toy environment
      :type env: GFlowNetEnv



   .. py:method:: __call__(states)

      Implement  this function to call the get_reward method of the appropriate Proxy
      Class (EI, UCB, Proxy, Oracle etc).

      :param states:
      :type states: ndarray