Signals 4 · free daily AI digest

Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging

Paper recorded by Signals 4 on 2026-09-16 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-16 on arXiv · recorded by Signals 4 on 2026-09-17

Category: cs.LG · 机器学习 · first seen 2026-09-17

Abstract

Can a logged dataset visit every hidden state frequently and still be exponentially uninformative about a target policy's value? We show that it can when the logger depends on history. For every horizon $H \ge 3$, we construct two POMDPs with at most two latent states per stage, three actions, and a common logger with three memory states. Action coverage, belief coverage, and two behavior-marginal

Read on arXiv →

#15 most recent of 215 cs.LG papers we have recorded · ↑ newer: RISC-V and machine learning: a survey · ↓ older: How Model Growth, Recursion, and Boundary Operators Influence Scaling
Cite this page: Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging: the #15 most recent of 215 cs.LG papers we have recorded (as of 2026-09-16). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/exponential-hardness-of-off-policy-evaluation-under-history-dependent-logging.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions