AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Potential Outcome Rankings for Counterfactual Decision Making

Yuta Kawakami, Jin Tian

AAAI 2026 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 1 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
increase per-action sample size N' from 30 to 3000 (ablation)PoR estimator · SCM A, K=3S_PoR(1,2,3) estimate vs truth 0.666: 0.557 -> 0.635Improved
increase per-action sample size N' from 30 to 3000 (ablation)PoB estimator · SCM A, K=3S_PoB(1) estimate vs truth 0.666: 0.561 -> 0.650Improved
increase number of candidate actions K from 3 to 20 (ablation)PoR estimator · SCM C (N'=3000)absolute error of PoR: 0.022 -> 0.256Hurt
increase number of candidate actions K from 3 to 20 (ablation)PoB estimator · SCM C (N'=3000)absolute error of PoB: 0.015 -> 0.023Hurt
reduce per-action sample size from 3000 to 300 at K=20 (ablation)PoR estimator · SCM Cabsolute error of PoR: 0.256 -> 0.431Hurt
drop rank invariance and use bounds instead of point estimate (ablation)PoR bounds · SCM B, K=3 (N'=3000)upper bound of S_PoR vs true 0.500: 0.873 upper bound, 0.000 lower bound, true value 0.500Mixed
use PoR ranking instead of RoE ranking for treatment choicetreatment decision · Coagulation Thromb.countranking of treatments: RoE: B>H>S (0.994, 0.917, 0.873); PoR best (B,S,H) 0.277Mixed
use PoB instead of RoE to assess the best treatment Btreatment decision · Coagulation Thromb.countshare of patients for whom B is best: B is optimal for only 49% of patientsMixed

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