CS886 - Multiagent Systems - Winter 2025

Course Description

This course will introduce key challenges that arise within multiagent systems, namely how should we design and build agents and shape interactions in complex settings so as to best support cooperation and coordination. We will consider human users to also be a critical part of any system and so will also consider some of the fundamental challenges associated with recent alignment approaches

Learning Outcomes:

• • Discover research challenges raised by today's multiagent systems.
• • Learn whether newly proposed research directions and solutions from academia or industry address these challenges.
• • Identify opportunities for further research and undertake some novel research.
• • Improve your technical writing and presentation skills.

The seminar will primarily consist of reading, reviewing, and presenting research papers. There will be two papers assigned to each class period.

The course assumes a basic knowledge of computer science or mathematics. While not formal prerequisies, some background in multiagent systems and AI might be useful. The following are good resources:

• Artificial Intelligence: Foundations of Computational Agents by D. Poole and A. Mackworth
• Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations by Y. Shoham and K. Leyton-Brown
• Reinforcement Learning: An Introduction by R. Sutton and A. Barto

Course Requirements

Paper Presentations and Discussion:

In every lecture, two students will each present a research paper and lead a discussion. All students are expected to present one or two papers during the course. Presentations are conference-style and take at most 30 minutes. The presenter should have sufficient background knowledge of the related work to answer broad questions and lead the class discussion. See the reading list for a list of the papers. Presenters should email their slides to the instructor before the lecture. While figures and animations may be borrowed with proper attribution, slides must be created independently.

Developing oral presentation skills is important for graduate students. To provide feedback, all students (excluding presenters reviewing their own presentation) are required to submit a review for each of the two presentations after each lecture (see link above). Reviews should address the questions outlined in this document. Reviews are due by 12:01 pm (noon) the day after the presentation. Presenters will have access to their anonymized reviews.

Paper Critiques:

In every lecture, two students will each present a critique of a research paper. This will occur immediately after the presentation of the paper. The critique should take at most 10 minutes and will serve as a basis of further discussion. Effective critiques will address key assumptions, limitations, connections to other research, and potential future directions. Students may use slides to structure their critiques, but this is optional. Students are not permitted to critique the same paper they present.

Paper Reviews:

Before each lecture, all students must read the two assigned papers and submit a brief review (up to 1000 words) for both of them (see link above). Reviews should address the questions outlined in this document: PaperReview.txt. Reviews are due by 7:00 am on the day the paper is presented. These anonymized reviews will be shared with the class. Students presenting or critiquing a paper are exempt from writing reviews for their assigned paper and any other papers presented on the same day.

Projects:

Students will conduct original research in the area of multiagent systems, with a focus on cooperation, coordination or alignment. Projects should ideally be done in groups of two. If you strongly prefer doing a project individually or in a larger group, send email to the instructor explaining your reasons. You are encouraged to discuss your project topic with the instructor before submitting your proposal.

• Project proposal (due Feb 14):
Project proposals should be emailed as a PDF to the instructor. These should be no more than two pages that succinctly describe what you plan to work on, your planned methodology, the form of results you hope to have by the end of the term, and and some related work in the area.

• Project presentation (March 31):
At the end of term, groups will present their work to the class in a conference-style presentation.

• Final project report (due April 11):
The report should be formatted using the ICML template. The report should not have more than 12 pages, excluding the bibliography. Appendices are permitted and do not count towards the page limit, but you should not expect the reader to read them.

Grading

Grades for this seminar will be calculated as follows:

Use of Generative AI

Academic Integrity

Note that students are not generally permitted to submit the same work for credit in multiple classes. For example, if students have reviewed or presented one of the papers in another seminar class, they should avoid reviewing or presenting it again for this class.

General University Policy

• Academic Integrity: In order to maintain a culture of academic integrity, members of the University of Waterloo community are expected to promote honesty, trust, fairness, respect and responsibility. Check the Office of Academic Integrity's website for more information.

  All members of the UW community are expected to hold to the highest standard of academic integrity in their studies, teaching, and research. This site explains why academic integrity is important and how students can avoid academic misconduct. It also identifies resources available on campus for students and faculty to help achieve academic integrity in — and out — of the classroom.

• Grievance: A student who believes that a decision affecting some aspect of his/her university life has been unfair or unreasonable may have grounds for initiating a grievance. Read Policy 70 — Student Petitions and Grievances, Section 4. When in doubt please be certain to contact the department's administrative assistant who will provide further assistance.

• Discipline: A student is expected to know what constitutes academic integrity, to avoid committing academic offenses, and to take responsibility for his/her actions. Check the Office of Academic Integrity for more information. A student who is unsure whether an action constitutes an offense, or who needs help in learning how to avoid offenses (e.g., plagiarism, cheating) or about "rules" for group work/collaboration should seek guidance from the course professor, academic advisor, or the Undergraduate Associate Dean. For information on categories of offenses and types of penalties, students should refer to Policy 71 — Student Discipline. For typical penalties, check Guidelines for the Assessment of Penalties.

• Avoiding Academic Offenses: Most students are unaware of the line between acceptable and unacceptable academic behaviour, especially when discussing assignments with classmates and using the work of other students. For information on commonly misunderstood academic offenses and how to avoid them, students should refer to the Office of Academic Integrity's site on Academic Misconduct and the Faculty of Mathematics Cheating and Student Academic Discipline Policy.

• Appeals: A decision made or penalty imposed under Policy 70, Student Petitions and Grievances (other than a petition) or Policy 71, Student Discipline may be appealed if there is a ground. A student who believes he/she has a ground for an appeal should refer to Policy 72, Student Appeals.

Note for Students with Disabilities

AccessAbility Services, located in Needles Hall, Room 1401, collaborates with all academic departments to arrange appropriate accommodations for students with disabilities without compromising the academic integrity of the curriculum. If you require academic accommodations to lessen the impact of your disability, please register with AccessAbility at the beginning of each academic term.

Mental Health Support

All of us need a support system. We encourage you to seek out mental health supports when they are needed. Please reach out to Campus Wellness and Counselling Services.
We understand that these circumstances can be troubling, and you may need to speak with someone for emotional support. Good2Talk is a post-secondary student helpline based in Ontario, Canada that is available to all students.

Territorial Acknowledgement

We acknowledge that we live and work on the traditional territory of the Attawandaron (Neutral), Anishinaabeg, and Haudenosaunee peoples. The University of Waterloo is situated on the Haldimand Tract, the land promised to the Six Nations that includes ten kilometres on each side of the Grand River.

Credits

Thanks to Diogo Barradas for providing the template for this website.