AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding

Hongseok Namkoong, Ramtin Keramati, Steve Yadlowsky, Emma Brunskill

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Importance-weighted OPE estimators · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use the loss-minimization bound instead of the naive worst-case boundconfounded OPE sensitivity analysis · Sepsis simulator, Gamma*=5.0design sensitivity: 1.75 -> 5.6Improved
use the loss-minimization bound instead of the naive boundconfounded OPE sensitivity analysis · Autism simulator, Gamma*=1.0design sensitivity: 1.32 -> 2.78Improved
use the loss-minimization bound instead of the naive boundconfounded OPE sensitivity analysis · Sepsis simulator, Gamma*=2.0interval informativenessImproved
use the loss-minimization bound instead of the naive boundconfounded OPE sensitivity analysis · Autism simulator Case IIcertified policy superiority: certified up to Gamma=4.2Improved
use robust bounds instead of standard OPE assuming sequential ignorabilitystandard OPE · Autism simulator Case I, Gamma*=2.0policy ranking correctnessImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy