skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: Faster No-Regret Learning Dynamics for Extensive-Form Correlated and Coarse Correlated Equilibria
Award ID(s):
1733556
PAR ID:
10392168
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
AAAI-22 Reinforcement Learning in Games (RLG) Workshop
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Fractional Dirac materials (FDMs) feature a fractional energy-momentum relation E(k)∼|k|α, where α(<1) is a real noninteger number, in contrast to that in conventional Dirac materials with α=1. Here we analyze the effects of short- and long-range Coulomb repulsions in two- and three-dimensional FDMs. Only a strong short-range interaction causes nucleation of a correlated insulator that takes place through a quantum critical point. The universality class of the associated quantum phase transition is determined by the correlation length exponent ν−1=d−α and dynamic scaling exponent z=α, set by the band curvature. On the other hand, the fractional dispersion is protected against long-range interaction due to its nonanalytic structure. Rather, a linear Dirac dispersion gets generated under coarse graining, and the associated Fermi velocity increases logarithmically in the infrared regime, thereby yielding a two-fluid system. Altogether, correlated FDMs unfold a rich landscape accommodating unconventional emergent many-body phenomena. 
    more » « less