EE 546: Learning and Control for Multi-agent Systems
(Winter 2026)

Course Information

Instructor: Jing Yu

Time & location: Tuesdays and Thursdays 2.30am-3.50pm, ARC G07

Office hours: By appointment

Course Description

This is a special topics course in advanced control theory. The core question we will investigate is: Who does what when in learning and control, in the face of coupling, communication limitations, heterogeneity, and scalability considerations. The introduction slides can be found here.

Prerequisites:This is a theory-forward class, so it is expected that students are prepared to engage with formal derivations and proofs. Students should be familiar with the following:

• Control theory (e.g., state-space theory, stability, etc.)

• Probability (e.g., CLT, conditional expectation, etc.)

• Linear algebra (e.g., SVD, PSD matrices, etc.)

• Basic real analysis & convex optimization

Course Topics

Theme 1: Distributed (learning-enabled) control for complex networks 

• Optimal control synthesis with structural constraints 

• Parameterizations for control design (structured linear control, GNN, etc. ) 

Theme 2: Sensor/actuator architecture in the face of communication and uncertainty 

• Submodular optimization 

• A Sample of classic sensor/actuator placement problems 

Theme 3: “Control-oriented” learning for networks

• Statistical learning theory for system identification (federated sysID, learning mixtures of dynamical systems, etc.) 

• Learning distributed controllers (policy optimization)

• Collaborative bandit problems 

Tentative Schedule

The first 7 weeks of lectures will introduce theoretical foundations. Handwritten lecture notes can be accessed here. The rest of the quarter will consist of student-led paper discussions (presentation schedule). 

Week 1 - 2 

• Parameterization, optimization, and co-design of optimal distributed controllers under communication limitations 

Week 3 - 4

• Concentration inequalities for system identification 

• Consensus algorithms 

Week 4 - 5

• Introduction to submodular optimization & related problems

Week 5 - 7 

• Bandits and collaborative bandit 

Week 7 - 10 

• Student-led paper discussions on themed papers

Final's week 

• Student project symposium 

Grading 

20% participation 

• In-class discussion. 

40% paper presentation (theory forward) 

• Present a theory paper and lead an in-class discussion 

• Two to three 1-on-1 meetings with the instructor to prepare for the presentation/discussion. 

• Choose from list of themed papers (or choose your own, subject to instructor approval) 

• You are graded on the clarity of the presentation, thoughtfulness of the paper discussion, and ability to field questions. 

40% final project (application forward) 

• Pairs of 2 students work on an application (engineering systems, simulators, reproducing results in the papers, algorithms, etc.) that applies concepts and algorithms learnt in class. This is meant to build on the papers discussed in class. Single-person teams require instructor approval. 

Accommodation & Accessibility

The UW’s policy, including more information about how to request an accommodation, is available at Religious Accommodations Policy (https://registrar.washington.edu/staffandfaculty/religious-accommodations-policy/). Accommodations must be requested within the first two weeks of this course using the Religious Accommodations Request form (https://registrar.washington.edu/students/religious-accommodations-request/). 

If you have already established accommodations with Disability Resources for Students (DRS), please communicate your approved accommodations to me at your earliest convenience so we can discuss your needs in this course. If you have not yet established services through DRS, but have a temporary health condition or permanent disability that requires accommodations (conditions include but not limited to; mental health, attention-related, learning, vision, hearing, physical or health impacts), you are welcome to contact DRS at 206-543-8924 or uwdrs@uw.edu or disability.uw.edu. DRS offers resources and coordinates reasonable accommodations for students with disabilities and/or temporary health conditions. Reasonable accommodations are established through an interactive process between the student, instructor, and DRS. It is the policy and practice of the University of Washington to create inclusive and accessible learning environments consistent with federal and state law.