AI RESEARCH
On the Exploitability of FTRL Dynamics
arXiv CS.LG
•
ArXi:2604.05129v1 Announce Type: cross In this paper we investigate the exploitability of a Follow-the-Regularized-Leader (FTRL) learner with constant step size $\eta$ in $n\times m$ two-player zero-sum games played over $T$ rounds against a clairvoyant optimizer. In contrast with prior analysis, we show that exploitability is an inherent feature of the FTRL family, rather than an artifact of specific instantiations.