Module 16: Reinforcement Learning

Learning from interaction rather than labeled examples. This module introduces the RL problem formulation and the core algorithms for learning decision-making policies.

What You’ll Learn¶

• Agents, environments, states, actions, and rewards

• Markov decision processes and the Bellman equations

• Dynamic programming, Monte Carlo, and temporal-difference learning

• Q-learning and deep Q-networks (DQN)

• Implementing RL agents in practice

Lecture Materials¶

• 📊 Lecture Slides (PDF)

• 📓 Lecture notebook: Reinforcement Learning for Decision Making

Prerequisites¶

• Modules 10–11

• Basic probability

Reference¶

Raschka & Mirjalili, Machine Learning with PyTorch and Scikit-Learn, Chapter 19.