tutorials.examples.train_hypergrid_exploration_examples
=======================================================

.. py:module:: tutorials.examples.train_hypergrid_exploration_examples

.. autoapi-nested-parse::

   A simplified version of GFlowNet training on the HyperGrid environment, focusing on the core concepts.
   This script implements Trajectory Balance (TB) training with minimal features to aid understanding.

   Example usage:
   python train_hypergrid_simple.py --ndim 2 --height 8 --epsilon 0.1

   Key differences from the full version:
   - Only implements TB loss
   - No wandb integration
   - Simpler architecture with shared trunks
   - Basic command line options



Attributes
----------

.. autoapisummary::

   tutorials.examples.train_hypergrid_exploration_examples.parser


Functions
---------

.. autoapisummary::

   tutorials.examples.train_hypergrid_exploration_examples._print_mode_stats
   tutorials.examples.train_hypergrid_exploration_examples.build_gflownet
   tutorials.examples.train_hypergrid_exploration_examples.main
   tutorials.examples.train_hypergrid_exploration_examples.print_final_results
   tutorials.examples.train_hypergrid_exploration_examples.train


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

.. py:function:: _print_mode_stats(env)

.. py:function:: build_gflownet(preprocessor, env, uniform_pb = False, n_hidden_layers = 3, n_noisy_layers = 0, std_init = 0.5)

.. py:function:: main(args)

.. py:data:: parser

.. py:function:: print_final_results(all_results, width = 80)

   Print final results in a pretty formatted table.


.. py:function:: train(env, preprocessor, device, lr, lr_logz, batch_size, n_iterations, epsilon, temperature, use_noisy_layers, use_replay_buffer, seed, uniform_pb, validation_interval, validation_samples)