Evaluating the Robustness of Off-Policy Evaluation

Yuta Saito, Takuma Udagawa, Haruka Kiyohara, Kazuki Mogi, Yusuke Narita and Kei Tateno

Discussion papers from Research Institute of Economy, Trade and Industry (RIETI)

Abstract: Off-policy Evaluation (OPE), or offline evaluation in general, evaluates the performance of hypothetical policies leveraging only offline log data. It is particularly useful in applications where the online interaction involves high stakes and expensive settings such as precision medicine and recommender systems. Since many OPE estimators have been proposed and some of them have hyperparameters that need to be tuned, there is an emerging challenge for practitioners to select and tune OPE estimators for their specific application. Unfortunately, identifying a reliable estimator from results reported in research papers is often difficult because the current experimental procedure evaluates and compares the estimators’ performance on a narrow set of hyperparameters and evaluation policies. Therefore, it is difficult to know which estimator is safe and reliable to use. In this work, we develop Interpretable Evaluation for Offline Evaluation (IEOE), an experimental procedure to evaluate OPE estimators’ robustness to changes in hyperparameters and/or evaluation policies in an interpretable manner. Then, using the IEOE procedure, we perform extensive evaluation of a wide variety of existing estimators on the Open Bandit Dataset, a large-scale public real-world dataset for OPE. We demonstrate that our procedure can evaluate the estimators’ robustness to the hyperparameter choice, helping us avoid using unsafe estimators. Finally, we apply IEOE to real-world e-commerce platform data and demonstrate how to use our protocol in practice.

Pages: 20 pages
Date: 2023-06
New Economics Papers: this item is included in nep-mfd
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.rieti.go.jp/jp/publications/dp/23e041.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eti:dpaper:23041

Access Statistics for this paper

More papers in Discussion papers from Research Institute of Economy, Trade and Industry (RIETI) Contact information at EDIRC.
Bibliographic data for series maintained by TANIMOTO, Toko ().