econ.EM · 2026-11-04 · No. 163
Econometrics, 2026-11-04.
1 new papers in econ.EM. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
Regret-based Characterization, Information Limits, and the Sample Complexity of Auditing Adaptive Policies
Irene Aldridge
econ.EM · cs.IT · cs.LG
A policy can earn its performance by where it locates on average or by reacting to information. For any Markov policy $π$ in a finite-horizon MDP, let $ν$ be its open-loop marginal, which plays $π$'s average action distribution at each step. We show that $J(π)-J(ν)$ equals $\sum_t tr Cov(Q^ν_t,π_t)$ under endogenous dynamics. Audits based on immediate costs alone can have the wrong sign. Writing the covariance as a joint-versus-product gap...
This edition is part of The Daily Abstract — econ.EM archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.