Overview

Accountability is one of the pillars of trustworthy AI, and causality plays a pivotal role in defining concepts that are critical for enabling accountable decision processes in AI systems. In this seminar course, we will review recent advances in designing accountable AI agents, with emphasis put on designs that utilize casual reasoning. We will focus on the following three main topics: (i) actual causality and responsibility attribution, (ii) explainability and agents’ incentives, and (iii) accountability in reinforcement learning.

The course will be a combination of lectures, student-led presentations and discussion sessions. Although prior knowledge of casualty is not needed, basic understanding of decision making frameworks will be helpful.

Course Staff

To reach us,  please use the following email address: accountable-AI-s2023-tutors@mpi-sws.org. Please use personal emails only for communication that is not related to this  seminar.

Important Information

We will post the most important announcements below, but additional information may be communicated via email. Please check this website regularly for updates.

  • The registration deadline is April 12th. Interested students should register through https://seminars.cs.uni-saarland.de/.
  • Please see the tab Structure and Grading for more information about the course structure. Tentative schedule and reading assignments are available in the tab Schedule and Reading List.
  • The introductory lecture will take place on Thursday April 20 at 10:15am. Location: Room 005 at MPI-SWS (Building E1 5).