Research map / Learning theory and algorithms / Combinatorial and search optimization
Learning to search efficiently for causally near-optimal treatments
Samuel Håkansson, Viktor Lindblom, Omer Gottesman, Fredrik D Johansson
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use function approximation (_F) instead of historical-smoothing tables (_H) for outcome model (ablation) | CDP/CG/NDP · MIMIC-III antibiotics | search time at near-optimal efficacy | Improved |
| learned policies CDP/CG/NDP versus emulated doctor policy | CDP, CG, NDP · MIMIC-III antibiotics | mean search length: 1.38 -> 1.26 | Improved |
| use CDP or CG instead of model-free NDP | constrained policy search · MIMIC-III antibiotics | search time at near-optimal efficacy | Improved |
| increase training set size from 50 to 75000 samples | CDP and CG · synthetic DGP | efficacy and mean number of actions | Improved |
| increase training set size from 50 to 75000 samples | NDP · synthetic DGP | efficacy | Mixed |
Closest papers by meaning
- Designing Optimal Dynamic Treatment Regimes: A Causal Reinforcement Learning Approach (ICML 2020 · similarity 0.89)
- Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes (NeurIPS 2019 · similarity 0.88)
- Optimal Experiments for Partial Causal Effect Identification (NeurIPS 2026 · similarity 0.85)
- Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning (ICLR 2024 · similarity 0.85)
- ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized Experiments (AAAI 2025 · similarity 0.85)
- EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes (NeurIPS 2024 · similarity 0.85)
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.
