Video
Description
In this session, participants will focus on a specific method of Temporal Difference Learning called Tabular Q Learning. Participants will learn the theory behind Q Learning, implement the different components bit by bit and combine these components to solve the robot in a maze scenario.
Lecture Slides
StarAi Lecture 3 & 4 TabularQ slides
Exercise
Follow the link below to access the exercises for lecture 3:
Lecture 3 Exercise: Tabular Q FrozenLake
Exercise Solutions
Follow the link below to access the exercise solutions for lecture 3:
Exercise Solutions: Tabular Q FrozenLake
Additional Learning Material
- Sutton & Barto’s Reinforcement Learning: An Introduction - Chapter 5 read intro and summary, Chapter 6 intro, section 6.1 to 6.3 + 6.5 (other sections optional but good to read), Chapter 7 read intro and summary