src.gridmind.policies.parameterized.continuous_action_mlp_policy
================================================================

.. py:module:: src.gridmind.policies.parameterized.continuous_action_mlp_policy


Classes
-------

.. autoapisummary::

   src.gridmind.policies.parameterized.continuous_action_mlp_policy.ContinuousActionMLPPolicy


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

.. py:class:: ContinuousActionMLPPolicy(observation_shape: tuple, num_actions: int, num_hidden_layers: int = 0, in_features: int = 16, out_features: int = 16, use_bias: 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:: num_hidden_layers
      :value: 0



   .. py:attribute:: in_features
      :value: 16



   .. py:attribute:: out_features
      :value: 16



   .. py:attribute:: hidden_layers


   .. py:method:: _create_hidden_layer(use_bias: bool)


   .. py:method:: forward(x)


   .. py:method:: get_action(state)


   .. py:method:: get_statistic(state)


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


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