| layout | title | nav_order | permalink |
|---|---|---|---|
home |
Overview |
1 |
/:path/ |
Instructor: Tom Silver
Time and Location: TBD
Course description: Planning and learning are essential for intelligent robots. In this course, we will consider how planning and learning can be combined to accomplish difficult tasks over long time horizons with sparse feedback, complicated constraints, and multiple forms of uncertainty. The course will be in two parts. In Part 1, the instructor will lecture on planning and students will complete problem sets to establish a common technical foundation. In Part 2, students will present papers on machine learning for planning while working on extended final projects.
Key questions: Throughout the course, we will revisit the following questions:
- What learning and planning should happen in the factory vs. the wild?
- Where on the learning-planning spectrum should robots be?
- What planning models should be learned?
- How should we taxonomize learning-for-planning methods?
- What objectives should we use to train and evaluate these methods?
- To what extent are learning and planning necessary for general-purpose robotics?
Prerequisites: This course is designed for graduate students and advanced undergraduates. Students should be very comfortable with Python and fairly comfortable with machine learning. Familiarity with planning and robots is encouraged but not required.