Reinforcement Learning

Introduction

This course introduces learners to the fundamentals and advanced methods of Reinforcement Learning (RL). It begins with core principles, including Markov Decision Processes (MDPs), RL components, and problem formulation, before moving into solution strategies such as dynamic programming, Monte Carlo methods, and temporal-difference learning. Learners then explore advanced approaches like Deep Q-Networks (DQN), policy gradients, and modern RL techniques. Practical experience is emphasized through hands- on projects, including solving OpenAI Gym environments (CartPole, MountainCar) and a mini-project where students design, train, and evaluate their own RL agent.