prt-rl 0.6.0

Python Research Toolkit - Reinforcement Learning

prt-rl is part of the broader Python Research Toolkit ecosystem and provides a clean, mathematically grounded collection of reinforcement learning algorithms.
Its primary goal is clarity, pedagogy, and research exploration—not raw performance.

This library is designed for researchers, students, and practitioners who want to understand why RL algorithms work, how their mathematics map to code, and what practical implementation details matter in real systems.

Unlike high-performance libraries such as TorchRL, RLlib, and skrl, prt-rl focuses on transparency, composability, and conceptual depth. Every algorithm is implemented with an emphasis on readability, modularity, and annotated code that highlights both the underlying equations and the implementation tips that make them work in practice.

⚠️ Note: This repository is under active development. APIs, file structure, and module organization may change as the project evolves. Backward compatibility is not guaranteed until version 1.0.

Documentation

Installation, Getting Started, and API guides can be found in the full documentation:

➡️ https://prt-rl.readthedocs.io/en/latest/

---

Contributing

Contributions are welcome!
Please open an issue before submitting a pull request so that new features or bug fixes can be discussed beforehand.