Lecture Materials

Lecture materials for this course are given below. Note the associated refresh your understanding and check your understanding polls will be posted weekly.

Topic	Videos (on Canvas/Panopto)	Course Materials
Introduction to Reinforcement Learning	Lecture 1	Lecture 1 Draft Slides [Post class version] Additional Materials: High level introduction: SB (Sutton and Barto) Chp 1 Linear Algebra Review Probability Review Python Tutorial
Tabular MDP planning	Lecture 2	Lecture 2 Slides (pre-class) [Post class, annotated] Additional Materials: SB (Sutton and Barto) Chp 3, 4.1-4.4
Tabular RL policy evaluation	Lecture 3	Lecture 3 Slides (pre-class) [Post class, with annotations] Additional Materials: SB (Sutton and Barto) Chp 5.1, 5.5, 6.1-6.3 David Silver's Lecture 4 [link]
Q-learning	Lecture 4	Lecture 4 Slides (preclass) (post class with annotations) Additional Materials: SB (Sutton and Barto) Chp 5.2, 5.4, 6.4-6.5, 6.7
Policy Gradient	Lecture 5, 6	Lecture 5 Slides [Post lecture with annotations] Lecture 6 Slides [Post class annotations] Lecture 7 Slides [Post class annotations] Additional Materials: SB (Sutton and Barto) Chp 13
Imitation Learning and Learning from Human Input and Batch RL	Lecture Videos	Lecture 7 Slides [Post class annotations] Lecture 8 Slides (preclass) [Post class with annotations] Lecture 9 Slides [Post class] Lecture 9 Guest lecture part slides Lecture 10 Slides [Post class] Additional Materials:
Data Efficient RL	Lecture Videos	Lecture 11 Slides [Post class annotations] Lecture 12 Slides (Tuesday Feb 18) [Post class annotations] Lecture 13 Slides [Post class annotations] Lecture 14 Slides [Post class annotations] Additional Materials: Bandit Algorithms Book Section 7.1
Ethics and Society Guest Lecture	Lecture Videos	Lecture 9 Part Guest Slides 1 Lecture 15 Guest Slides 2
Monte Carlo Tree Search and Conquering Go	Lecture Videos	Lecture 15 Draft slides [Post class with annotations]
LLMS and RL Guest Lecture and Wrap Up	Lecture Videos	Lecture 16 (pre class draft) [post class, annotated] Additional Materials: "Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning" [Neurips 2024].