wtf is udacity-reinforcement?

This repository is a collection of learning projects from Udacity's Deep Reinforcement Learning course. It documents one person's journey through increasingly complex techniques for teaching machines to make decisions and learn from experience. Reinforcement learning is a way to train AI systems to get better at tasks by rewarding good decisions and penalizing bad ones, much like how you'd train a dog. The repository shows how to build these systems using different mathematical approaches, starting with simple methods and moving to more sophisticated ones. The early projects (Dynamic Programming, Monte Carlo, Temporal Difference) cover foundational techniques that form the backbone of the field. Later projects tackle real-world problems like teaching a robot to walk, controlling a pendulum, or managing a trading portfolio. Each project is typically a Jupyter Notebook, which is an interactive document that shows both the code and explanations side by side. The structure reveals a clear progression. The first few lessons are marked as complete and teach the core theory, how to calculate the best actions in a problem space. Once those foundations are solid, the projects branch into practical applications. Some involve simulated environments where an AI learns to navigate or control movement. Others explore policy gradient methods, which is a different mathematical approach to training these systems. The mix of completed and in-progress tasks suggests this is an active learning journal, not a finished library or tool. This repository would be useful for anyone trying to learn reinforcement learning themselves, whether as a student working through the same Udacity course or someone self-studying this field. It's a personal study archive rather than a tool you'd use directly, but it could serve as a reference for how to structure your own projects or as inspiration for what techniques to explore next. The README doesn't provide much documentation beyond the project checklist, so most value comes from reading the individual notebooks themselves.