Dive into the fundamentals of Reinforcement Learning with this comprehensive lecture covering key concepts such as Markov Decision Processes, policy optimization, and model-free evaluation. Explore important components of RL, categorize RL agents, and understand Bellman's Equation through practical examples like the Inverted Pendulum and a Toy Maze. Learn about Monte Carlo methods for evaluation and control, as well as Temporal Difference Control, providing a solid foundation for understanding and implementing RL algorithms.
Overview
Syllabus
Intro
Markov Decision Process
Reinforcement Learning Problem
Policy optimization
Example: Inverted Pendulum
Important Components in RL
Categorizing RL agents
Toy Maze Example
Model free evaluation
Monte Carlo Evaluation
Model Free Control
Bellman's Equation
Monte Carlo Control
Temporal Difference Control
Taught by
Pascal Poupart
