Machine Learning Lunch Meeting

You are cordially invited to the weekly Machine Learning Lunch Meetings every Friday 12:30-1:30pm, starting on Sept 6, 2024 in Computer Sciences room 1221.  Faculty members from Computer Science, Statistics, ECE, and other departments will discuss their latest groundbreaking research in machine learning. This is an opportunity to network with faculty and fellow researchers, and to learn about the cutting-edge research being conducted in our university.  

Plese see https://sites.google.com/view/wiscmllm/home for the schedule. To receive future weekly talk announcements, please subscribe to our mailing list at https://lists.cs.wisc.edu/mailman/listinfo/mllm using your CS or Wisc email address. After entering your email address, you will receive a confirmation email. You will be added to the mailing list only after responding to that email.

Speaker: Jerry Zhu (CS)

Abstract: We study the game modification problem, where a benevolent game designer or a malevolent adversary modifies the reward function of a zero-sum Markov game so that a target deterministic or stochastic policy profile becomes the unique Markov perfect Nash equilibrium and has a value within a target range, in a way that minimizes the modification cost. We characterize the set of policy profiles that can be installed as the unique equilibrium of a game and establish sufficient and necessary conditions for successful installation. We propose an efficient algorithm that solves a convex optimization problem with linear constraints and then performs random perturbation to obtain a modification plan with a near-optimal cost.