Reinforcement Learning 2023

Lectures

Lecture	Video	Materials
Lecture 1. From stochastic optimization to Reinforcement Learning	lecture 1 vid part 1, lecture 1 vid part 2	lecture 1 notes
Lecture 2. Intro to policy gradient	lecture 2 vid part 1, lecture 2 vid part 2, lecture 2 vid part 3	lecture 2 notes
Lecture 3. Looking deeper into REINFORCE	lecture 3 vid part 1, lecture 3 vid part 2	lecture 3 notes
Lecture 4. Hamilton-Jacobi-Bellman	lecture 4 vid part 1, lecture 4 vid part 2	lecture 4 notes
Lecture 5. Actor-critic	lecture 5 vid part 1, lecture 5 vid part 2	lecture 5 notes
Lecture 6. More on Policy Gradient	lecture 6 vid part 1, lecture 6 vid part 2	lecture 6 notes
Lecture 7. Critic Learing	lecture 7 vid part 1, lecture 7 vid part 2	lecture 7 notes
Lecture 8. TRPO and PPO	lecture 8 vid part 1, lecture 8 vid part 2	lecture 8 notes
Lecture 9. Soft Actor Critic	lecture 9 vid part 1	lecture 9 notes

Seminar	Video	Materials
Seminar 1. RL Terminology	sem 1 vid	sem 1 notes
Seminar 2. Discrete-time systems	N/A	sem 2 colab, sem 2 colab solutions
Seminar 3. Policy Gradient	sem 3 vid	sem 3 colab, sem 3 colab solutions
Seminar 4.	sem 4 vid	sem 4 colab, sem 4 colab solutions
Seminar 5. Actor-Critic	sem 5 vid	sem 5 colab, sem 5 colab solutions
Seminar 6. Actor-Critic	sem 6 vid	sem 6 colab, sem 6 colab solutions
Seminar 9. Sending a satellite into orbit with MPC	N/A	sem 9 colab, sem 9 colab solutions
Seminar 10. Linear-Quadratic Regulators	N/A	sem 10 colab, sem 10 colab solutions

Assignment	Colab
Assignment 1. Reinforce	HW 1 colab
Assignment 2. Actor-Critic Policy Gradient	HW 2 colab
Assignment 3. Proximal Policy Optimization	HW 3 colab
Assignment 4. Online Actor-Critic	HW 4 colab