gfn.gym.line
============

.. py:module:: gfn.gym.line


Classes
-------

.. autoapisummary::

   gfn.gym.line.Line


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

.. py:class:: Line(mus, sigmas, init_value, n_sd = 4.5, n_steps_per_trajectory = 5, device = 'cpu', debug = False)

   Bases: :py:obj:`gfn.env.Env`


   Mixture of Gaussians Line environment.

   .. attribute:: mus

      The means of the Gaussians.

   .. attribute:: sigmas

      The standard deviations of the Gaussians.

   .. attribute:: n_sd

      The number of standard deviations to consider for the bounds.

   .. attribute:: n_steps_per_trajectory

      The number of steps per trajectory.

   .. attribute:: mixture

      The mixture of Gaussians.

   .. attribute:: init_value

      The initial value of the state.


   .. py:method:: backward_step(states, actions)

      Performs a backward step in the environment.

      :param states: The current states.
      :param actions: The actions to take.

      :returns: The previous states.



   .. py:attribute:: init_value


   .. py:method:: is_action_valid(states, actions, backward = False)

      Checks if the actions are valid.

      :param states: The current states.
      :param actions: The actions to check.
      :param backward: Whether to check for backward actions.

      :returns: `True` if the actions are valid, `False` otherwise.



   .. py:method:: log_partition(condition=None)

      Returns the log partition of the reward function.



   .. py:method:: log_reward(final_states)

      Computes the log reward of the environment.

      :param final_states: The final states of the environment.

      :returns: The log reward.



   .. py:attribute:: mixture


   .. py:attribute:: mus


   .. py:attribute:: n_sd
      :value: 4.5



   .. py:attribute:: n_steps_per_trajectory
      :value: 5



   .. py:attribute:: sigmas


   .. py:method:: step(states, actions)

      Performs a step in the environment.

      :param states: The current states.
      :param actions: The actions to take.

      :returns: The next states.