Concept-driven Off Policy Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Majumdar, Ritam, Teversham, Jack, Parbhoo, Sonali
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929608581971968
author Majumdar, Ritam
Teversham, Jack
Parbhoo, Sonali
author_facet Majumdar, Ritam
Teversham, Jack
Parbhoo, Sonali
contents Evaluating off-policy decisions using batch data poses significant challenges due to limited sample sizes leading to high variance. To improve Off-Policy Evaluation (OPE), we must identify and address the sources of this variance. Recent research on Concept Bottleneck Models (CBMs) shows that using human-explainable concepts can improve predictions and provide better understanding. We propose incorporating concepts into OPE to reduce variance. Our work introduces a family of concept-based OPE estimators, proving that they remain unbiased and reduce variance when concepts are known and predefined. Since real-world applications often lack predefined concepts, we further develop an end-to-end algorithm to learn interpretable, concise, and diverse parameterized concepts optimized for variance reduction. Our experiments with synthetic and real-world datasets show that both known and learned concept-based estimators significantly improve OPE performance. Crucially, we show that, unlike other OPE methods, concept-based estimators are easily interpretable and allow for targeted interventions on specific concepts, further enhancing the quality of these estimators.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19395
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Concept-driven Off Policy Evaluation
Majumdar, Ritam
Teversham, Jack
Parbhoo, Sonali
Machine Learning
Artificial Intelligence
Evaluating off-policy decisions using batch data poses significant challenges due to limited sample sizes leading to high variance. To improve Off-Policy Evaluation (OPE), we must identify and address the sources of this variance. Recent research on Concept Bottleneck Models (CBMs) shows that using human-explainable concepts can improve predictions and provide better understanding. We propose incorporating concepts into OPE to reduce variance. Our work introduces a family of concept-based OPE estimators, proving that they remain unbiased and reduce variance when concepts are known and predefined. Since real-world applications often lack predefined concepts, we further develop an end-to-end algorithm to learn interpretable, concise, and diverse parameterized concepts optimized for variance reduction. Our experiments with synthetic and real-world datasets show that both known and learned concept-based estimators significantly improve OPE performance. Crucially, we show that, unlike other OPE methods, concept-based estimators are easily interpretable and allow for targeted interventions on specific concepts, further enhancing the quality of these estimators.
title Concept-driven Off Policy Evaluation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.19395