Learning Objectives

Learning Objectives for Lecture 7: Function Approximation (Sutton and Barto 2018) 🎯

• Let’s talk about Exam 1 and Final Project!
• Value Function Approximation.
• On-Policy Approximation.
• Limitations of Off-Policy Approximation.
• MountainCarContinuous-v0 environment using gymnasium & numpy.

Taxonomy of Reinforcement Learning

Sutton, Richard S., and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. 2nd ed. Cambridge, MA: MIT Press.