📘 Overview
This course explored both classical RL algorithms (MDPs, Monte Carlo, SARSA, Q-Learning) and modern deep RL techniques (policy gradients, DQN, PPO, SAC).
A strong emphasis was placed on experimentation and projects, from implementing tabular methods to building agents in complex environments.
Trends such as imitation learning, multi-agent systems, Curriculum learning and offline RL were also introduced.
👉 Official Teaching Guide (Deusto)