Edreate.com – Deep Reinforcement Learning Course

Welcome 👋
This repository contains the codebase used in lessons from Edreate’s Deep Reinforcement Learning (DRL) course.

👉 For the full learning experience—including in-depth write-ups, mathematical formulas, video explanations, and structured chapters—visit the course page:
🔗 edreate.com/courses/deep-reinforcement-learning

---

🤝 Community

Join our Discord server for learning, collaboration, and Q&A.

---

🚀 Setup Instructions

For complete setup details, see:
Setting Up Coding Environment and Dependencies

Quickstart (TL;DR)

You’ll need Python and uv installed.

# install uv (if not already installed)
pip install uv

# install all dependencies into .venv
uv sync

# activate the virtual environment
source .venv/bin/activate

# launch Jupyter
uv run jupyter notebook

💡 You can also use your favorite code editor (VS Code, PyCharm, etc.).

---

🌟 Algorithms Covered (Course Highlights)

This repository tracks the main algorithms from the Deep RL course.
Completed ones link to full lessons, others are marked Coming Soon!

✅ Available Now

• Deep Q-Learning Learn how DQN scales beyond Q-tables and train agents directly with neural networks.

🔜 Coming Soon

• Vanilla Policy Gradient (VPG) – direct optimization of stochastic policies
• Actor–Critic (A2C) – combining value functions with policy learning
• Proximal Policy Optimization (PPO) – stable, scalable policy gradients
• Advanced Methods – SAC and more

🚧 More lessons and code will be added as the course grows!

---

📄 License

This project is licensed under the terms of the
LICENSE file in the root of this repository.