test_box_polar_utils
====================

.. py:module:: test_box_polar_utils


Classes
-------

.. autoapisummary::

   test_box_polar_utils.TestBoxCartesianDistribution
   test_box_polar_utils.TestBoxCartesianEndToEnd
   test_box_polar_utils.TestBoxCartesianEnvironment
   test_box_polar_utils.TestBoxCartesianPBDistribution


Functions
---------

.. autoapisummary::

   test_box_polar_utils.test_mixed_distributions


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

.. py:class:: TestBoxCartesianDistribution

   Tests for BoxCartesianDistribution.


   .. py:method:: env()


   .. py:method:: pf_estimator(env, pf_module)


   .. py:method:: pf_module()


   .. py:method:: test_log_prob_exit_at_boundary(env, pf_estimator)

      Exit at boundary should have finite log_prob (learned Bernoulli).



   .. py:method:: test_log_prob_finite(env, pf_estimator)

      Log probabilities should be finite for valid actions.



   .. py:method:: test_no_exit_from_s0(env, pf_estimator)

      Exit from s0 should have log_prob = -inf.



   .. py:method:: test_sample_non_s0_in_range(env, pf_estimator)

      From non-s0, sampled actions should be >= delta.



   .. py:method:: test_sample_s0_in_range(env, pf_estimator)

      From s0, sampled actions should be in [0, 1] (full space coverage).



   .. py:method:: test_sample_shape(env, pf_estimator)

      Sampled actions should have correct shape.



.. py:class:: TestBoxCartesianEndToEnd

   End-to-end tests for the Cartesian Box implementation.


   .. py:method:: env()


   .. py:method:: pb_estimator(env)


   .. py:method:: pf_estimator(env)


   .. py:method:: test_backward_trajectory_reaches_s0(env, pb_estimator)

      A backward trajectory should reach s0.



   .. py:method:: test_reward_function(env)

      Reward function should return expected values.



   .. py:method:: test_trajectory_stays_in_bounds(env, pf_estimator)

      A trajectory should stay within [0, 1]^2.



.. py:class:: TestBoxCartesianEnvironment

   Tests for the Box environment with Cartesian semantics.


   .. py:method:: env()


   .. py:method:: test_backward_step_subtracts_action(env)

      Backward step should subtract action from state.



   .. py:method:: test_exit_action_valid(env)

      Exit actions should be valid for non-s0 states.



   .. py:method:: test_forward_backward_roundtrip(env)

      Forward then backward should return to original state.



   .. py:method:: test_forward_step_adds_action(env)

      Forward step should add action to state.



   .. py:method:: test_is_action_valid_boundary(env)

      Actions shouldn't push state past boundary.



   .. py:method:: test_is_action_valid_non_s0_forward(env)

      From non-s0, forward actions should be >= delta.



   .. py:method:: test_is_action_valid_s0_forward(env)

      From s0, forward actions should be in [0, 1] (full space coverage).



.. py:class:: TestBoxCartesianPBDistribution

   Tests for BoxCartesianPBDistribution (backward policy).


   .. py:method:: env()


   .. py:method:: pb_estimator(env, pb_module)


   .. py:method:: pb_module()


   .. py:method:: test_log_prob_near_origin(env, pb_estimator)

      Log prob for near-origin states going to s0 should be 0.

      When near origin (any dimension <= delta), BTS is forced and log_prob = 0.
      For numerical robustness, any action from a near-origin state is treated
      as BTS since that's the only valid action anyway.



   .. py:method:: test_sample_mixed_dims_near_origin(env, pb_estimator)

      States with mixed dims (some < delta, some >= delta) should handle correctly.



   .. py:method:: test_sample_near_origin_to_s0(env, pb_estimator)

      States near origin should go directly to s0.



   .. py:method:: test_sample_non_origin_valid(env, pb_estimator)

      Backward actions from non-origin should be valid.



   .. py:method:: test_sample_shape(env, pb_estimator)

      Sampled backward actions should have correct shape.



.. py:function:: test_mixed_distributions(n_components, n_components_s0)

   Tests the `DistributionWrapper` class.

   :param n_components: The number of components for non-s0 states.
   :param n_components_s0: The number of components for s0.