Course Number: 151-0607-00L
Lecture Hall: CAB G 11
Time: Tue, 14-16 (Lecture), 16-17 (Exercise)
Lecturer: Jonas Buchli
Head Assistant: Farbod Farshidian
Office hours: Thu, 17:30-18:30, Room ML J 37.1.
Hardcopy of script will be given in the lecture. Lecture slides will be available for download after the lecture.
The following books are useful for additional reading:
These are very nice and quite elementary books, we recommend buying them.
Additional reading material here
Lecture 1 | Introduction / Principle of optimality | Ch 1.1 | Lecture 1 Slides (updated 22.2.) |
---|---|---|---|
Lecture 2 | Discrete optimal control problem, Bellman Equation | Ch 1.2 | Lecture 2 Slides |
Lecture 3 | Continuous-time optimal control problem, HJB Equation | Ch 1.3 | Lecture 3 Slides (updated 3.3.) |
Lecture 4 | SQP / SLQ / ILQC | Ch 1.5-6 | Lecture 4 Slides (updated 10.3.) |
Lecture 5 | ILQC / LQR | Ch 1.6-7 | Lecture 5 Slides (updated 17.3.) |
Lecture 6 | LQR/LQG | Ch 1.7-8 | Lecture 6 Slides (updated 24.3.) |
Lecture 7 | MDP RL, Policy evaluation | Ch 2.1-2.8 | Lecture 7 Slides (updated 31.3.) |
Lecture 8 | Policy iteration, Value iteration, Monte Carlo RL | Lecture 8 Slides (updated 17.4.) | |
Lecture 9 | Monte Carlo RL, Q-learning | Lecture 9 Slides (Add'l on reading materials page.) | |
Lecture 10 | Function approximation, Intro to SDE and Fokker Planck Eq. | Lecture 10 Slides (updated 28.4.) | |
Lecture 11 | Path integral optimal control | Lecture 11 Slides | |
Lecture 12 | PI-based algorithms, Optimal motion control pipeline | Lecture 12 Slides (updated 12.5.) | |
Lecture 13 | Policy gradient / Finite difference | Lecture 12 Slides | |
Lecture 14 | Summary and exam discussion |
Sign up for interview for Exercise 3 using your group ID: https://ethz.doodle.com/bsi7gvkycvrmht6t
Further details TBA in lecture and exercise hour.
Handout | Code | Presentation | Exercise Submission | |||
---|---|---|---|---|---|---|
Ex 1 Handout | matlab1.zip | Ex 1 Slides | ||||
Ex 2 Handout | matlab2.zip | Ex 2 Slides | ||||
Ex 3 Handout | matlab3.zip | Ex 3 Slides |