The chapter provides an introduction to deep reinforcement learning (DRL), a field that combines reinforcement learning (RL) with deep learning to solve complex decision-making tasks. DRL has achieved significant success in various domains, including healthcare, robotics, and finance, by leveraging the ability of deep neural networks to learn from high-dimensional inputs. The chapter covers the motivation for DRL, the basic concepts of machine learning and deep learning, and the formal framework of RL. It discusses different approaches to learning policies, including value-based and policy-based methods, and explores the challenges of generalization and exploration-exploitation in online settings. The chapter also reviews key algorithms such as Q-learning, fitted Q-learning, deep Q-networks (DQNs), and their variants, highlighting improvements like double DQN and dueling network architecture. Finally, it touches on the broader perspectives of DRL, including its applications, successes, and remaining challenges.The chapter provides an introduction to deep reinforcement learning (DRL), a field that combines reinforcement learning (RL) with deep learning to solve complex decision-making tasks. DRL has achieved significant success in various domains, including healthcare, robotics, and finance, by leveraging the ability of deep neural networks to learn from high-dimensional inputs. The chapter covers the motivation for DRL, the basic concepts of machine learning and deep learning, and the formal framework of RL. It discusses different approaches to learning policies, including value-based and policy-based methods, and explores the challenges of generalization and exploration-exploitation in online settings. The chapter also reviews key algorithms such as Q-learning, fitted Q-learning, deep Q-networks (DQNs), and their variants, highlighting improvements like double DQN and dueling network architecture. Finally, it touches on the broader perspectives of DRL, including its applications, successes, and remaining challenges.