TorchWM Documentation
======================

TorchWM is a modular PyTorch library for world models, latent-dynamics planning,
and representation learning workflows (Dreamer, JEPA, IRIS, DiT, and more).

.. toctree::
   :maxdepth: 1
   :caption: Get Started

   getting_started
   installation

.. toctree::
   :maxdepth: 1
   :caption: User Guides

   public_api
   operators_guide
   training_guide
   inference_guide
   environments_guide
   environments/index
   datasets/nuplan
   cli
   package_overview
   world_models_guide
   tutorials/world_model_env_rl_libraries
   world_models_deep_dive

.. toctree::
   :maxdepth: 1
   :caption: Algorithms

   dreamer
   jepa
   iris
   dit
   genie

.. toctree::
   :maxdepth: 1
   :caption: Reference

   api_reference
   configs_reference

.. toctree::
   :maxdepth: 1
   :caption: Development

   contributing
   benchmarks