GH Repository · FareedKhan-dev
all-rl-algorithms
Implementation of all RL algorithms in a simpler way
- stars
- 1,941
- 30-day movement
- +41/day
- Related entries
- 60
- Connections
- 1
agent-apprlpython/uvpythonJupyter Notebookopenaireinforcement-learningllmagent
A repository collecting implementations of reinforcement learning algorithms, written to be simpler to read and follow. The code is provided as Jupyter Notebooks and uses a Python toolchain managed with uv.
You want readable, notebook-based reference implementations of RL algorithms rather than a heavy framework.
Use it to
- Study RL algorithm implementations in notebooks
- Run and modify the algorithms in Python
- Use the code as a base for your own RL experiments
- Explore RL in LLM/agent contexts per the repo topics
For Developers and students learning reinforcement learning
- Role
- agent-app
- Language
- Jupyter Notebook
- Licence
- MIT
- Forks
- 376
- Open issues
- 1
- Last push
- 2025-08-29
topicsreinforcement-learningpythonjupyterllmagentsopenai