AI Paper Atlas

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

Learning Robust Decision Policies from Observational Data

Muhammad Osama, Dave Zachariah, Peter Stoica

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Confounding-robust policy evaluation · 0 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
Choose treatments by minimizing a conformal upper cost limit instead of minimizing expected costRobust policy · Synthetic blood-pressure data20% tail costImproved
Choose treatments by minimizing a conformal upper cost limit instead of minimizing expected costRobust policy · Synthetic blood-pressure dataexpected costHurt
Use a robust policy rather than the past policyRobust policy · IHDP synthetic outcomes, equal dispersion and higher untreated dispersion20% tail costImproved
Use a robust policy rather than the linear expected-cost policyIHDP synthetic outcomes, equal dispersion and higher untreated dispersion · IHDP synthetic outcomes20% tail costImproved
Adapt treatment assignment to higher treated-outcome dispersionRobust policy · IHDP synthetic outcomes, higher treated dispersiontail costImproved
Use a linear expected-cost policy when treated outcomes have higher dispersionLinear policy · IHDP synthetic outcomes, higher treated dispersiontail costHurt
Provide a conformal cost limit for each decisionRobust policy · IHDP test dataexceedance probability: 18.6% vs 20%Improved

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