gfn.gym.box_cartesian
=====================

.. py:module:: gfn.gym.box_cartesian


Classes
-------

.. autoapisummary::

   gfn.gym.box_cartesian.BoxCartesian


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

.. py:class:: BoxCartesian

   Bases: :py:obj:`gfn.gym.box.BoxPolar`


   Box environment with Cartesian per-dimension action validation.

   Inherits all behavior from :class:`BoxPolar` (init, step, backward_step,
   reward, log_partition, norm, make_random_states). Overrides only
   :meth:`is_action_valid` to use per-dimension bounds instead of polar norm
   constraints.

   Use with the Cartesian estimators/distributions in
   ``box_cartesian_utils.py``.

   .. seealso:: :class:`BoxPolar` for the original polar norm-based variant.


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

      Checks if the actions are valid (Cartesian per-dimension semantics).

      For Cartesian actions:
      - Forward from s0: action[i] >= 0 and action[i] <= 1
      - Forward from non-s0: action[i] >= delta and state[i] + action[i] <= 1
      - Backward: state[i] - action[i] >= 0
      - Backward to s0: if all resulting dims < delta, action must equal state

      :param states: The current states.
      :param actions: The actions to be taken.
      :param backward: Whether the actions are backward actions.

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