Metadata-Version: 2.4
Name: dist_classicrl
Version: 0.1.0
Summary: A high-performance Python package for distributed classical reinforcement learning algorithms with support for single-threaded, parallel, and MPI-distributed Q-Learning training.
Author-email: Javier Moralejo Piñas <j.moralejo.pinas@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/j-moralejo-pinas/dist_classicrl
Project-URL: Source, https://github.com/j-moralejo-pinas/dist_classicrl
Project-URL: Tracker, https://github.com/j-moralejo-pinas/dist_classicrl/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.13
Description-Content-Type: text/x-rst
License-File: LICENSE.txt
License-File: AUTHORS.rst
Requires-Dist: gymnasium
Requires-Dist: matplotlib
Requires-Dist: mpi4py
Requires-Dist: numpy
Provides-Extra: dev
Requires-Dist: pyright; extra == "dev"
Requires-Dist: pre-commit; extra == "dev"
Requires-Dist: ruff; extra == "dev"
Requires-Dist: pydoclint; extra == "dev"
Requires-Dist: docformatter; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"
Requires-Dist: pyupgrade; extra == "dev"
Provides-Extra: test
Requires-Dist: pytest; extra == "test"
Requires-Dist: pytest-cov; extra == "test"
Provides-Extra: code-quality
Requires-Dist: ruff; extra == "code-quality"
Requires-Dist: pydoclint; extra == "code-quality"
Requires-Dist: pyright; extra == "code-quality"
Provides-Extra: format
Requires-Dist: ruff; extra == "format"
Requires-Dist: docformatter; extra == "format"
Requires-Dist: pyupgrade; extra == "format"
Provides-Extra: docs
Requires-Dist: sphinx; extra == "docs"
Requires-Dist: sphinx-autoapi; extra == "docs"
Requires-Dist: sphinx_rtd_theme; extra == "docs"
Requires-Dist: sphinxcontrib-napoleon; extra == "docs"
Dynamic: license-file

==============
dist_classicrl
==============

A Python package for distributed classical reinforcement learning algorithms.

.. image:: https://img.shields.io/pypi/v/dist_classicrl.svg
    :alt: PyPI-Server
    :target: https://pypi.org/project/dist_classicrl/
.. image:: https://img.shields.io/badge/license-MIT-blue.svg
    :alt: License
    :target: https://github.com/j-moralejo-pinas/dist_classicrl/blob/main/LICENSE.txt
.. image:: https://img.shields.io/badge/python-3.8+-blue.svg
    :alt: Python Version
    :target: https://www.python.org/downloads/

|

🎯 **Project Description**
--------------------------

**dist_classicrl** provides high-performance, scalable implementations of classic reinforcement learning algorithms with support for distributed training. The library focuses on Q-Learning with multiple execution modes: single-threaded, parallel (multiprocessing), and distributed (MPI) training.

🚀 **Key Features**
-------------------

- 🚀 **Multiple Execution Modes**: Single-threaded, parallel, and MPI-distributed training
- ⚡ **High Performance**: Optimized implementations with vectorized operations and performance benchmarking
- 🎮 **Multi-Agent Support**: Built-in support for multi-agent environments
- 🔧 **Flexible Architecture**: Abstract base classes for easy extension and custom environments
- 🌐 **Standards Compliant**: Compatible with Gymnasium and PettingZoo environments (coming soon)

📚 **Documentation**
--------------------

**Essential Guides:**

- 📦 `Installation Guide <docs/installation.rst>`_ - Setup instructions and requirements
- 📊 `Performance Benchmarks <docs/benchmarks.rst>`_ - Benchmarking results and analysis
- 📚 `Tutorials <docs/tutorials.rst>`_ - Step-by-step guides for using the library
- 🤝 `Contributing Guidelines <CONTRIBUTING.rst>`_ - Development standards and contribution process
- 📄 `License <LICENSE.txt>`_ - License terms and usage rights
- 👥 `Authors <AUTHORS.rst>`_ - Project contributors and maintainers
- 📜 `Changelog <CHANGELOG.rst>`_ - Project history and version changes
- 📜 `Code of Conduct <CODE_OF_CONDUCT.rst>`_ - Guidelines for participation and conduct

---
