refine_plan.models.option
=========================

.. py:module:: refine_plan.models.option

.. autoapi-nested-parse::

   Class for options, which are temporally extended actions.

   Author: Charlie Street
   Owner: Charlie Street



Classes
-------

.. autoapisummary::

   refine_plan.models.option.Option


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

.. py:class:: Option(name, transition_list, reward_list)

   Bases: :py:obj:`object`


   An option is a temporally extended behaviour.

   Options are traditionally defined in terms of an initiation set I,
   a termination condition beta, and a policy pi.

   Here, we just define the option in terms of its transition probabilities
   (assuming no preemption occurs) and reward model.

   .. attribute:: _name

      The option's name

   .. attribute:: _transition_list

      The option's transition model

   .. attribute:: _reward_list

      The option's reward model


   .. py:method:: get_name()

      Return the option's name.

      :returns: The option's name



   .. py:method:: get_transition_prob(state, next_state)

      Return the transition probability for a (s,s') pair.

      Assumes there is only one precondition which holds for each state.

      :param state: The first state
      :param next_state: The next state

      :returns: The transition probability



   .. py:method:: get_reward(state)

      Return the reward for executing an option in a given state.

      :param state: The state we want to check

      :returns: The reward for the state



   .. py:method:: get_transition_prism_string()

      Return a PRISM string which captures all transitions for this option.

      :returns: The transition PRISM string



   .. py:method:: get_reward_prism_string()

      Return a PRISM string which captures all rewards for this option.

      :returns: The reward PRISM string