AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Gradient Regularized V-Learning for Dynamic Treatment Regimes

Yao Zhang, Mihaela van der Schaar

NeurIPS 2020 · Probabilistic and scientific modeling › Treatment effects · approach: Benchmarking treatment effect models · 2 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
GRV estimator vs AIPW for value estimation at n=1000 (treatment cost)GRV · Treatment cost trade-offMSE: .139 ˘ .006 -> .134 ˘ .004Improved
GRV vs AIPW at n=10000GRV · Treatment cost trade-offMSE: .023 ˘ .003 vs .022 ˘ .002No clear effect
GRV vs AIPW at n=1000 (survival)GRV · Survival rate maximizationMSE: .047 ˘ .005 -> .032 ˘ .002Improved
GRV vs IPW at n=1000 (survival)GRV · Survival rate maximizationMSE: .332 ˘ .035 -> .032 ˘ .002Improved
Increase training sample size 1000 to 10000GRV · Treatment cost trade-offMSE: .134 ˘ .004 -> .022 ˘ .002Improved
Learn DTR with GRV-B instead of IPW/BQLGRV-B · Treatment cost trade-off n=1000DTR value: .748 ˘ .002 -> .761 ˘ .003Improved
Learn DTR with GRV-B vs BQL (survival)GRV-B · Survival rate maximization n=5000DTR value: .198 ˘ .003 -> .224 ˘ .002Improved
Optimize all treatment rules together (GRV-S) instead of backward (GRV-B) (ablation)GRV · Treatment cost trade-off n=1000DTR value: .761 ˘ .003 -> .753 ˘ .004Hurt
GRV-S vs GRV-B in survival n=1000 (ablation)GRV · Survival rate maximization n=1000DTR value: .182 ˘ .004 -> .146 ˘ .005Hurt
Ablate the gradient regularizer (ablation)GRV · Appendix simulationsperformanceImproved
GRV-S vs BQL, survival n=10000GRV-S · Survival rate maximization n=10000DTR value: .215 ˘ .002 vs .213 ˘ .002No clear effect

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