Reproduce “Fictitious Play When Agents Are Not Expected-Utility Maximizers: A Geometric Analysis in $2$-Action Games” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hao Liang, Solaleh Mohammadi, Kaiqing Zhang
The authors study nonlinear fictitious play, which updates beliefs from opponents’ action frequencies but evaluates actions using payoff distributions rather than their means. In two-action games, finitely many sign-changing advantage crossings guarantee convergence to a ρ-Nash equilibrium in continuous and discrete time. However, a constructed 2×3 game cycles in continuous time under lower-tail CVaR with α = 1/5.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.