Research map / Reinforcement learning / Policy gradient and actor-critic
Trustworthy Policy Learning under the Counterfactual No-Harm Criterion
Haoxuan Li, Chunyuan Zheng, Yixiao Cao, Zhi Geng, Yue Liu, Peng Wu
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 |
|---|---|---|---|
| add counterfactual no-harm constraint (uFNA upper bound) to policy learning | CATE-based policy learning on IHDP and JOBS · IHDP and JOBS, cost 0-0.10 | true harm: Naive 19.12 vs No-Harm (u) 10.34 on IHDP (c=0) | Improved |
| add counterfactual no-harm constraint (wFNA upper bound) to policy learning | CATE-based policy learning on IHDP and JOBS · IHDP and JOBS, cost 0-0.10 | true harm: Naive 19.12 vs No-Harm (w) 5.98 on IHDP (c=0) | Improved |
| use the tighter uFNA bound instead of wFNA bound in the harm constraint (ablation) | No-Harm policy learning · IHDP and JOBS | reward: No-Harm (u) reward 496.93 vs No-Harm (w) 459.80 on IHDP (c=0); 1453.00 vs 1325.00 on JOBS | Improved |
| switch from CATE-based to recommendation-based utility without harm constraint | naive policy learning · IHDP | true harm: Naive CATE 19.12 vs Naive recommendation 64.36 (c=0) | Hurt |
| increase cost c(x) from 0 to 0.10 in harm-constrained policies (ablation) | No-Harm policy learning · IHDP and JOBS | true harm and reward: Reward and harm decrease with cost; welfare change does not change much | Mixed |
Closest papers by meaning
- Towards Safe Policy Learning under Partial Identifiability: A Causal Approach (AAAI 2024 · similarity 0.88)
- Learning Counterfactual Outcomes Under Rank Preservation (NeurIPS 2025 · similarity 0.86)
- Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings (NeurIPS 2025 · similarity 0.85)
- Policy Learning for Balancing Short-Term and Long-Term Rewards (ICML 2024 · similarity 0.85)
- Distributionally Robust Policy Learning under Concept Drifts (ICML 2025 · similarity 0.84)
- Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding (NeurIPS 2024 · similarity 0.84)
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.
