Welcome! 👋
This repository contains the final assignment for the course Reinforcement Learning II. The project implements and demonstrates a reinforcement learning agent using key techniques covered in the course.
├── doc/ # Source code (models, training, utils) ├── notebooks/ # (Optional) Jupyter notebooks for experiments ├── requirements.txt # List of dependencies ├── .gitignore # Files and folders ignored by Git └── README.md # Project overview and instructions
- Deep Q-Learning (DDQN)
To install the required dependencies, create a Python environment and install the packages from requirements.txt:
For running the project, execute the notebook tpfinal that you will find in the folder notebook.
The project includes training logs and plots showing the agent's performance over time. You’ll find them in the results/ directory or generated after training.
-
Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction
-
OpenAI Gymnasium documentation: https://gymnasium.farama.org
-
PyTorch documentation: https://pytorch.org
This project was developed as part of the final coursework for Reinforcement Learning II.
Feel free to explore, run, or adapt the code for your own experiments.
