Fundamentals of Reinforcement Learning

Specialization Introduction and Course Introduction

• Discover the roadmap for your specialization
• Meet the instructors and understand the course objectives
• Get familiar with the Reinforcement Learning textbook and prerequisites

An Introduction to Sequential Decision-Making

• Learn about sequential decision-making and evaluative feedback
• Explore action value estimation and the trade-off in decision-making
• Understand the concepts of optimistic initial values and upper-confidence bound action selection

Markov Decision Processes

• Gain insights into Markov Decision Processes and their significance
• Explore examples of MDPs and the reward hypothesis in Reinforcement Learning
• Complete graded assignments to describe and analyze MDPs

Value Functions & Bellman Equations

• Understand the concept of value functions and their role in decision-making
• Explore the history of Reinforcement Learning and the derivation of Bellman equations
• Learn about optimal policies and their connection to value functions

Dynamic Programming

• Differentiate between policy evaluation and control
• Explore iterative policy evaluation, policy improvement, and policy iteration
• Understand the efficiency and flexibility of dynamic programming in decision-making