Deep_reinforcement_learning_Course

Why we included this project

This repository holds the notebooks and code exercises from a free deep reinforcement learning course. It walks from Q-learning basics to policy-gradient methods like A2C and PPO, with implementations in both TensorFlow and PyTorch. Each unit pairs a short theoretical explanation with a runnable notebook and a concrete training environment, so you can watch an algorithm learn rather than only read about it. Besides classic gym-style tasks, it includes training in richer worlds like Unity-based games and VizDoom, which helps show how RL behaves in more interactive settings. The project has since been superseded by an updated Hugging Face course using modern libraries like Stable Baselines3, but this older repo remains handy as a reference for the original implementations and for comparing the two frameworks side by side.