tutorials.examples.train_bitsequence_non_autoregressive
=======================================================

.. py:module:: tutorials.examples.train_bitsequence_non_autoregressive

.. autoapi-nested-parse::

   Train a GFlowNet on the non-autoregressive BitSequence environment.

   This example trains a Trajectory Balance GFlowNet on the non-autoregressive
   BitSequence environment, where actions encode (position, word) pairs and
   positions can be filled in any order.

   The environment generates binary sequences and rewards those close (in Hamming
   distance) to a set of target "mode" sequences. The non-autoregressive
   formulation creates a richer DAG structure compared to the standard
   autoregressive (left-to-right) version, since the same terminal state can
   be reached via multiple orderings of position fills.

   Usage:
       python tutorials/examples/train_bitsequence_non_autoregressive.py
       python tutorials/examples/train_bitsequence_non_autoregressive.py --seq_size 8 --word_size 2 --n_modes 4



Attributes
----------

.. autoapisummary::

   tutorials.examples.train_bitsequence_non_autoregressive.DEFAULT_SEED
   tutorials.examples.train_bitsequence_non_autoregressive.parser


Functions
---------

.. autoapisummary::

   tutorials.examples.train_bitsequence_non_autoregressive.evaluate_l1
   tutorials.examples.train_bitsequence_non_autoregressive.main


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

.. py:data:: DEFAULT_SEED
   :value: 4444


.. py:function:: evaluate_l1(gflownet, env)

   Compute L1 distance between learned and true distributions.

   Only feasible for small environments (seq_size <= ~12).

   :param gflownet: Trained GFlowNet.
   :param env: The environment.

   :returns: Mean absolute difference between estimated and true distributions.


.. py:function:: main(args)

.. py:data:: parser