28 citations · 106 across the 20 of their papers we have counts for
11 papers · 1 filter
Strategic Distribution Shift of Interacting Agents via Coupled Gradient Flows
Lauren Conger, Franca Hoffmann, Eric Mazumdar +1
We propose a novel framework for analyzing the dynamics of distribution shift in real-world systems that captures the feedback loop between learning algorithms and the distribution…
On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback
Arnab Maiti, Kevin Jamieson, Lillian J. Ratliff
This paper studies a variant of two-player zero-sum matrix games, where, at each timestep, the row player selects row , the column player selects column , and the row player…
General sum stochastic games with networked information flows
Sarah H. Q. Li, Lillian J. Ratliff, Peeyush Kumar
Inspired by applications such as supply chain management, epidemics, and social networks, we formulate a stochastic game model that addresses three key features common across these…
Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms
Liyuan Zheng, Tanner Fiez, Zane Alumbaugh +2
The hierarchical interaction between the actor and critic in actor-critic based reinforcement learning algorithms naturally lends itself to a game-theoretic interpretation. We adop…
Minimax Optimization with Smooth Algorithmic Adversaries
Tanner Fiez, Chi Jin, Praneeth Netrapalli +1
This paper considers minimax optimization in the challenging setting where can be both nonconvex in and nonconcave in . Though such optimization…
Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation
Tanner Fiez, Lillian Ratliff
We study the role that a finite timescale separation parameter has on gradient descent-ascent in two-player non-convex, non-concave zero-sum games where the learning rate of pl…