CS 6756 - Learning for Robot Decision Making

Fall. 3 credits. Letter grades only.

Prerequisite: CS 4780 and demonstrated knowledge of linear algebra and probability. Enrollment limited to: graduate students or permission of instructor.

S. Choudhury.

Advances in machine learning have fueled progress towards deploying real-world robots from assembly lines to self-driving. Learning to make better decisions for robots presents a unique set of challenges. Robots must be safe, learn online from interactions with the environment, and predict the intent of their human partners. This graduate-level course dives into the various paradigms for robot learning and decision making and heavily focuses on algorithms, practical considerations, and features a strong programming component.

Outcome 1: Understand the fundamental concepts of online learning, reinforcement learning, and imitation learning in the context of robot decision making.

Outcome 2: Formulate existing as well as new problems in robotics as instances of these learning frameworks.

Outcome 3: Analyze tradeoffs in performance, sample complexity, and runtimes of various robot learning algorithms.

Outcome 4: Implement state-of-the-art robot learning algorithms and demonstrate performance on open-source benchmarks.