q_derived.base_q_derived_soft_policy
====================================

.. py:module:: q_derived.base_q_derived_soft_policy


Classes
-------

.. autoapisummary::

   q_derived.base_q_derived_soft_policy.BaseQDerivedSoftPolicy


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

.. py:class:: BaseQDerivedSoftPolicy(Q: Union[Any, Mapping], epsilon: float, num_actions: int)

   Bases: :py:obj:`gridmind.policies.soft.base_soft_policy.BaseSoftPolicy`


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


   .. py:attribute:: Q


   .. py:attribute:: epsilon


   .. py:attribute:: num_actions


   .. py:attribute:: action_space
      :value: None



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



   .. py:method:: get_epsilon()


   .. py:method:: set_epsilon(value: float)


   .. py:method:: decay_epsilon()
      :abstractmethod:



   .. py:method:: _get_random_action(action_mask=None)


   .. py:method:: get_action(state, action_mask=None)


   .. py:method:: get_action_prob(state, action, action_mask=None)


   .. py:method:: get_all_action_probabilities(states, action_mask=None)


   .. py:method:: get_action_deterministic(state, action_mask=None)


   .. py:method:: _get_greedy_action(state, action_mask=None)
      :abstractmethod: