tutorials.examples.train_graph_triangle
=======================================

.. py:module:: tutorials.examples.train_graph_triangle

.. autoapi-nested-parse::

   Minimal training example for a graph-building environment with node addition.

   This script demonstrates training a GFlowNet on a generic graph-building task where
   the policy can ADD_NODE, ADD_EDGE, or EXIT. The reward here encourages forming
   an undirected triangle (3 nodes, 3 edges).

   Run:
     python tutorials/examples/train_graph_build_nodes.py --device cpu --plot



Attributes
----------

.. autoapisummary::

   tutorials.examples.train_graph_triangle.parser


Classes
-------

.. autoapisummary::

   tutorials.examples.train_graph_triangle.TriangleReward


Functions
---------

.. autoapisummary::

   tutorials.examples.train_graph_triangle.init_env
   tutorials.examples.train_graph_triangle.init_gflownet
   tutorials.examples.train_graph_triangle.main
   tutorials.examples.train_graph_triangle.render_states


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

.. py:class:: TriangleReward(reward_val = 100.0, eps_val = 1e-06, device = 'cpu')

   Reward high if the graph is an undirected triangle, else a small epsilon.

   - Undirected triangle: exactly 3 nodes and edges {(0,1),(1,2),(0,2)} ignoring labels.


   .. py:method:: __call__(states)


   .. py:attribute:: device


   .. py:attribute:: eps_val
      :value: 1e-06



   .. py:attribute:: reward_val
      :value: 100.0



.. py:function:: init_env(device)

.. py:function:: init_gflownet(env, embedding_dim, num_conv_layers, device)

.. py:function:: main(args)

.. py:data:: parser

.. py:function:: render_states(states, evaluator)