method · first seen 4 Oct 2026
off-policy evaluation
Also: OPE
Estimating the value of a target policy using data logged by a different policy.
Mentions per week
PapersCodeDiscussion
Rank 99 on 16 Nov 2026 · 10 mentions in 28 days · 10 independent groups · papers · first seen 6 weeks ago · acceleration +1.71
Earliest sources
- Revealing After Overwriting: An Exponential POMDP OPE Lower Bound under History-Dependent LoggingPapers · 4 Oct 2026 · Youyu Luo, Pengzhan Zhou, Zhida Qin, Jia Wang, Zuotao Fu, Yu Liu, Chao Chen
- Variance-Optimal Off-Policy Evaluation with Conjunct Effect ModelingPapers · 6 Oct 2026 · Nicolò Felicioni, Michael Benigni, Maurizio Ferrari Dacrema, Paolo Cremonesi
- Efficient Best-of-N policy evaluation for inference-time alignmentPapers · 7 Oct 2026 · Jonas Schweisthal, Yuxin Wang, Athiya Deviyani, Stefan Feuerriegel, Dennis Fraue…
- Amortized Off-Policy Evaluation for LLMsPapers · 7 Oct 2026 · Younwoo Choi, Leo Feng, Vincent Liu, Haanvid Lee
- Budgeted Multi-Source Counterfactual Annotation for Off-Policy EvaluationPapers · 7 Oct 2026 · Biao Xiang, Ali Eshragh, Yuexing Li, Kai Wang
- What a Data Release Must Preserve for Off-Policy EvaluationPapers · 11 Oct 2026 · Kyungbok Lee, Yating Zou, Michael R. Kosorok
Latest sources
- Trajectory Density Ratios under Weak Support: A Survey across the SciencesPapers · 9 Nov 2026 · Wei Chen, Lihao Zhuang, Yubing Wu, Delu Zeng
- Variational Approach to Optimal IPS Estimator for Multi-logger Off-Policy EvaluationPapers · 9 Nov 2026 · Joon Suk Huh, Junghoon Seo
- JUBILEE: A Benchmark Environment for Off-Policy Evaluation in Debt CollectionsPapers · 7 Nov 2026 · Diego Silva Prado, Tiago Amaral Penteado de Jesus, Bruno Caldas de Souza, Cristi…
- Intra-Option Fitted Q-Evaluation: Evaluating Hierarchical Policies from Non-Hierarchical DataPapers · 7 Nov 2026 · Yunfu Deng, Josiah P. Hanna
- Adaptive Budgeted Data Acquisition for Robust Off-Policy Evaluation from Multiple LoggersPapers · 6 Nov 2026 · Amitakshar Biswas, Ruoqing Zhu
- High-Dimensional Off-Policy Evaluation without Sample Splitting using an Onsager CorrectionPapers · 5 Nov 2026 · Saksham Jain, Guillaume Braun, Masaaki Imaizumi
- When Category Means Move: A Paired-Support Audit of Recommendation Logs with Random InsertionsPapers · 3 Nov 2026 · Yu Zhang, Zhihan Wang, Yuhang Lu, Shuai Li
- Reinforcement Learning Under Runtime Confounding: Policy Learning and Off-Policy EvaluationPapers · 29 Oct 2026 · Raphael Kim, Michele Santacatterina, Ramin Zabih, Keith Barnatchez
- Model Selection for Off-Policy Evaluation via Bellman TournamentsPapers · 26 Oct 2026 · Lars van der Laan, Vasilis Syrgkanis, Nathan Kallus
- Prior-Data Fitted Networks for In-Context Off-Policy EvaluationPapers · 25 Oct 2026 · Shuguang Yu, Ting Li, Fan Zhou
- Next Best Action: Causal Constrained Offline RL for Business Action TargetingPapers · 19 Oct 2026 · Surya Ramachandiran, Yiming Li, Juan Mancilla-Caceres, Tao Ye, Jun Liu
- The Certification Exponent: Instance-Optimal Sequential Certification of Policy Improvement from History Dependent LogsPapers · 17 Oct 2026 · Rui Wang