Course Logistics (Spring 2024)
Course Description
The course will provide an in-depth view on the state-of-the-art learning methods for control and the know-how to apply these techniques. The first half of the course will focus on hand-on experience through exercises. The second half will focus on current research directions and open questions. Topics will span reinforcement learning, self-supervised learning, imitation learning, model-based learning and advanced deep learning architectures. By the end of the course, we hope you will be able to answer if learning based control can help solve the problem of your interest, how to formulate the problem in the learning framework and what algorithms to use. It will also prepare you for research in this area.
Course Format
This is a graduate course that will be a mix of seminar and lecture style classes. The plan is delve into technical details of particular algorithmic topics and follow it up with reading research papers. The course will involve working on a research project, three assignments and presenting papers.
Prerequisites
- Working knowledge of machine learning, deep learning, reinforcement learning is assumed.
- Experience with deep learning packages such as PyTorch or TensorFlow is assumed. Homeworks will be in Python.
- This is NOT a basic course in reinforcement learning, deep learning or AI. Although, this can be used as a concentration subject in AI.
Course Information
Class Time and Location
Time: Tuesday/Thursday 11am-12:30pm
Location: 1-190 (campus map)
Office Hours
| Office Hour (Location) | |
|---|---|
| Pulkit Agrawal | Tuesday 12:30pm-1:30pm (45-641H) |
| Idan Shenfeld | Monday 3:00pm-4:00pm (45-600A) |
| Jaedong Hwang | Wednesday 9:00am-10:00am (46-5189) |
| Nishant Abhangi | Friday 10:00am-11:00am (32-D451) |
| Quincy Johnson | Thursday 5:00pm-6:00pm (36-112) |
Class Forum
Forums are on Piazza (sign up with your MIT email address). Access Code for piazza will be given in the first lecture. You can also email the instructors for the access code. Please checkout the piazza regularly, we will make new annoncements on piazza.
Grading Policy
| Percentage | |
|---|---|
| Assignments | 50% |
| Class Participation | 10% |
| Final Projct | 40% |
Assignments are due week after the assignment release. You have five late days to be used in whole day increments over the term and it is only applicable to Assignments. While that time there will be no penalty. Students are required to grade others’ assignments in one homework. It is a part of the status report. You will also need to submit a brief status report every week (on Gradescope), contributing to the class participation grade.