Welcome to the Reinforcement Learning Tutorials repository. This repository contains the source code for a series of reinforcement learning tutorials, each associated with a Medium article. The tutorials cover a range of topics in reinforcement learning, from the basics to more advanced techniques.
Each tutorial is contained in its own directory, which includes the source code, a Jupyter notebook, and a link to the associated Medium article.
The first tutorial introduces the concept of reinforcement learning through a simple GridWorld environment. The agent learns to navigate a grid, avoiding obstacles and reaching a goal.
- Jupyter Notebook:
demo.ipynb - Medium Article: [https://towardsdatascience.com/reinforcement-learning-101-building-a-rl-agent-0431984ba178#f7b6]
The second tutorial introduces the implementation of the Q-Learning algorithm. In this tutorial we increase the complexity of the GridWorld environment, adding random obstacles.
- Python File
main.py
To run the tutorials, you will need Python 3.6 or later. The required Python packages can be installed with:
pip install -r requirements.txtTo run a tutorial, navigate to its directory and run the Jupyter notebook:
jupyter notebook gridworld.ipynbContributions are welcome! Please read the contributing guidelines first.
This project is licensed under the MIT License - see the LICENSE file for details.