Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling

Résumé

Off-policy learning (OPL) often involves minimizing a risk estimator based on importance weighting to correct bias from the logging policy used to collect data. However, this method can produce an estimator with a high variance. A common solution is to regularize the importance weights and learn the policy by minimizing an estimator with penalties derived from generalization bounds specific to the estimator. This approach, known as pessimism, has gained recent attention but lacks a unified framework for analysis. To address this gap, we introduce a comprehensive PAC-Bayesian framework to examine pessimism with regularized importance weighting. We derive a tractable PAC-Bayesian generalization bound that universally applies to common importance weight regularizations, enabling their comparison within a single framework. Our empirical results challenge common understanding, demonstrating the effectiveness of standard IW regularization techniques.
Fichier principal
Vignette du fichier
Unified_PAC_Bayesian_Study_of_Pessimism_for_Offline_Policy_Learning_with_Regularized_Importance_Sampling (6).pdf (2.83 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04606062 , version 1 (09-06-2024)

Identifiants

  • HAL Id : hal-04606062 , version 1

Citer

Imad Aouali, Victor-Emmanuel Brunel, David Rohde, Anna Korba. Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling. International Conference on Uncertainty in Artificial Intelligence, Jul 2024, Barcelona, Spain. ⟨hal-04606062⟩
6 Consultations
2 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More