📘 Reinforcement Learning Notes

👉 You can check out the full notes here: reinforcement_learning_note

There are already a number of excellent tutorials and lectures on Reinforcement Learning (RL), but I often find that many of them do not provide enough detail or explanation of the formulas behind the concepts. In many cases, key ideas are assumed to be obvious or straightforward—which can be a challenge for someone like me, who has a weaker background in mathematics but still wants a comprehensive understanding of RL.

To address this, I am writing these notes with the following goals:

✨ Clarity over assumptions I attempt to explain the theory as clearly as possible, breaking down formulas with step-by-step reasoning and intuitive examples.

🧩 Bridging theory and implementation Many Python RL implementations rely heavily on external libraries or are overly simplistic. My goal is to connect the mathematical foundation to practical code—without skipping over the details.

🙏 Acknowledging the giants This work builds on numerous outstanding sources, and I am forever indebted to them for their contributions.

📚 References

• Reinforcement Learning — Richard S. Sutton and Andrew G. Barto
• Mastering Reinforcement Learning with Python
• Grokking Deep Reinforcement Learning — Miguel Morales
• Introduction to Reinforcement Learning — David Silver (lecture series)
• PyTorch 1.x Reinforcement Learning Cookbook
• Deep Learning from Scratch 4