Research map / Reinforcement learning / Policy gradient and actor-critic
Confidence intervals and OPE benchmarks
Provide statistical guarantees, long-horizon methods, and risk-aware assessments for off-policy evaluation.
28 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2026) · an approach in Policy gradient and actor-critic, keyword cluster “ope · estimators · importance”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
4 papers in 2023–24 and 9 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 1.2% to 1.9%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2017 · Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation (NeurIPS 2017 · 23 citations)
- 2019 · Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning (NeurIPS 2019 · 28 citations)
- 2020 · Off-Policy Evaluation and Learning for External Validity under a Covariate Shift (NeurIPS 2020 · 11 citations)
- 2021 · Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning (NeurIPS 2021 · 61 citations)
- 2022 · Off-Policy Evaluation for Large Action Spaces via Embeddings (ICML 2022 · 3 citations)
- 2023 · Policy-Adaptive Estimator Selection for Off-Policy Evaluation (AAAI 2023 · 10 citations)
- 2024 · Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation (ICLR 2024 · 0 citations)
- 2025 · Off-Policy Evaluation under Nonignorable Missing Data (ICML 2025 · 0 citations)
- 2026 · Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation (ICML 2026 · 0 citations)
Earliest papers here
- Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation (NeurIPS 2017 · 23 citations)
- Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning (NeurIPS 2019 · 28 citations)
- Off-Policy Evaluation and Learning for External Validity under a Covariate Shift (NeurIPS 2020 · 11 citations)
What has been tried
24 papers here report 209 measured changes (a component added, removed or swapped, compared with a baseline): helped 61%, no clear effect 11%, hurt 18%, mixed 10%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add negative behavior-policy guidance to target-policy guidance | GaussianWorld distribution shift · value estimation bias | Helped | STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation (NeurIPS 2025 · 0 citations) | |
| Vary the target-cluster size | KuaiRec OPL · relative policy value | Mixed | Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits (ICLR 2025 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 13 papers; from OpenAlex and the papers' affiliations).
- Tokyo Institute of Technology · 2 papers
- Cornell University · 2 papers
- North Carolina State University · 2 papers
Use it
Download BibTeX of 27 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Importance-weighted OPE estimators (57 papers)
- Confounding-robust policy evaluation (47 papers)
Elsewhere in the topic
- Model-based RL with guarantees (245 papers)
- Regularized scalable deep value learning (216 papers)
- Temporal-difference and discounting theory (143 papers)
- Tree search and policy optimization (109 papers)
- Safety layers and shielding (85 papers)
- Variance-reduced policy gradients (79 papers)
- Actor-critic theory (76 papers)
- Off-policy actor-critic with expressive policies (71 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).