Sequential Off-Policy Learning with Logarithmic Smoothing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Haddouche, Maxime, Sakhi, Otmane
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909034400972800
author Haddouche, Maxime
Sakhi, Otmane
author_facet Haddouche, Maxime
Sakhi, Otmane
contents Off-policy learning enables training policies from logged interaction data. Most prior work considers the batch setting, where a policy is learned from data generated by a single behavior policy. In real systems, however, policies are updated and redeployed repeatedly, each time training on all previously collected data while generating new interactions for future updates. This sequential off-policy learning setting is common in practice but remains largely unexplored theoretically. In this work, we present and study a simple algorithm for sequential off-policy learning, combining Logarithmic Smoothing (LS) estimation with online PAC-Bayesian tools. We further show that a principled adjustment to LS improves performance and accelerates convergence under mild conditions. The algorithms introduced generalise previous work: they match state-of-the-art offline approaches in the batch case and substantially outperform them when policies are updated sequentially. Empirical evaluations highlight both the benefits of the sequential framework and the strength of the proposed algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10664
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sequential Off-Policy Learning with Logarithmic Smoothing
Haddouche, Maxime
Sakhi, Otmane
Machine Learning
Off-policy learning enables training policies from logged interaction data. Most prior work considers the batch setting, where a policy is learned from data generated by a single behavior policy. In real systems, however, policies are updated and redeployed repeatedly, each time training on all previously collected data while generating new interactions for future updates. This sequential off-policy learning setting is common in practice but remains largely unexplored theoretically. In this work, we present and study a simple algorithm for sequential off-policy learning, combining Logarithmic Smoothing (LS) estimation with online PAC-Bayesian tools. We further show that a principled adjustment to LS improves performance and accelerates convergence under mild conditions. The algorithms introduced generalise previous work: they match state-of-the-art offline approaches in the batch case and substantially outperform them when policies are updated sequentially. Empirical evaluations highlight both the benefits of the sequential framework and the strength of the proposed algorithms.
title Sequential Off-Policy Learning with Logarithmic Smoothing
topic Machine Learning
url https://arxiv.org/abs/2506.10664