FareedKhan-dev/all-rl-algorithms resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1918 stars · 367 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A collection of Jupyter Notebook implementations of 18 reinforcement learning algorithms written from scratch in Python with NumPy and PyTorch. It is an educational resource prioritizing readability over performance, including a cheat sheet for quick reference.

Use cases

• learn reinforcement learning algorithms from scratch
• understand how RL algorithms work under the hood
• study RL fundamentals before applying them to LLMs
• find a quick reference cheat sheet for RL algorithms
• experiment with RL algorithm implementations in notebooks
• teach reinforcement learning concepts to beginners

When to choose

• you want readable, educational implementations rather than optimized code
• you are a beginner learning RL step by step
• you prefer interactive Jupyter notebooks for experimentation
• you need a quick reference for RL formulas and pseudocode

When to avoid

• you need a production-ready or performance-optimized RL library
• you want advanced features or a stable API for building applications
• you need distributed or large-scale RL training

Facets

learning-resource · maturity active

machine-learning reinforcement-learning developer-tools reinforcement-learning machine-learning tutorials education python reinforcement-learning educational jupyter-notebooks from-scratch cheat-sheet pytorch llm-alignment

Member repositories

For agents

markdown · JSON · MCP: product_card(name="FareedKhan-dev/all-rl-algorithms")