src.gridmind.policies.parameterized.atari.atari_policy
======================================================

.. py:module:: src.gridmind.policies.parameterized.atari.atari_policy


Attributes
----------

.. autoapisummary::

   src.gridmind.policies.parameterized.atari.atari_policy.model


Classes
-------

.. autoapisummary::

   src.gridmind.policies.parameterized.atari.atari_policy.AtariPolicy


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

.. py:class:: AtariPolicy(observation_shape, num_actions, channel_first: bool = True)

   Bases: :py:obj:`gridmind.policies.parameterized.base_parameterized_policy.BaseParameterizedPolicy`


   Helper class that provides a standard way to create an ABC using
   inheritance.


   .. py:attribute:: channel_first
      :value: True



   .. py:attribute:: conv1


   .. py:attribute:: conv2


   .. py:attribute:: conv3


   .. py:attribute:: fc1


   .. py:attribute:: policy_logits


   .. py:method:: _get_conv_output_size(x)

      Helper function to compute the size of the flattened output after convolutions.



   .. py:method:: forward(x)


   .. py:method:: add_batch_dim_if_necessary(state)


   .. py:method:: get_actions(states)


   .. py:method:: get_action(state)


   .. py:method:: get_action_prob(state, action)


   .. py:method:: update(state, action)


.. py:data:: model