This repository contains Jupyter Notebooks and code examples from a book on deep reinforcement learning. It covers classic RL algorithms, value-based methods (DQN, Double DQN), policy gradient methods (PPO, A3C, TRPO), actor-critic algorithms (DDPG, TD3, SAC), and advanced topics like distributional RL and inverse RL. Implementations use TensorFlow with the OpenAI Gym toolkit.