7 papers
Linear Last-Iterate Convergence Rates for Optimistic Learning in Harmonic Games
John Lazarsfeld, Anas Barakat, Jacob Abernethy +4
We prove that the last iterate of Optimistic Follow-The-Regularized-Leader (OFTRL) converges at a linear rate to a Nash equilibrium in multiplayer harmonic games. Our result holds…
When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
John Lazarsfeld, Anas Barakat, Georgios Piliouras +2
This paper studies the convergence of the Optimistic Multiplicative Weights Update algorithm (OMWU) in two player zero-sum games. Recent works have identified instances on which th…
Deep Incentive Design with Differentiable Equilibrium Blocks
Vinzenz Thoma, Georgios Piliouras, Luke Marris
Automated design of multi-agent interactions with desirable equilibrium outcomes is inherently difficult due to the computational hardness, non-uniqueness, and instability of the r…
Solving Zero-Sum Convex Markov Games
Fivos Kalogiannis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Ian Gemp +1
We contribute the first provable guarantees of global convergence to Nash equilibria (NE) in two-player zero-sum convex Markov games (cMGs) by using independent policy gradient met…
Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play
John Lazarsfeld, Georgios Piliouras, Ryann Sim +1
This paper investigates the sublinear regret guarantees of two non-no-regret algorithms in zero-sum games: Fictitious Play, and Online Gradient Descent with constant stepsizes. In…
Online Learning in Stabilized Linear Dynamical Games with Adversarial Disturbances
Anas Barakat, John Lazarsfeld, Georgios Piliouras +1
We study online learning in linear dynamical games where multiple strategic agents act on a shared state evolving according to a linear dynamical system subject to adversarial dist…
Optimism Without Regularization: Constant Regret in Zero-Sum Games
John Lazarsfeld, Georgios Piliouras, Ryann Sim +1
This paper studies the optimistic variant of Fictitious Play for learning in two-player zero-sum games. While it is known that Optimistic FTRL -- a regularized algorithm with a bou…