Saved in:
Bibliographic Details
Main Authors: Li, Shaoang, Li, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.15073
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915501385449472
author Li, Shaoang
Li, Jian
author_facet Li, Shaoang
Li, Jian
contents Non-stationary multi-armed bandits enable agents to adapt to changing environments by incorporating mechanisms to detect and respond to shifts in reward distributions, making them well-suited for dynamic settings. However, existing approaches typically assume that reward feedback is available at every round - an assumption that overlooks many real-world scenarios where feedback is limited. In this paper, we take a significant step forward by introducing a new model of constrained feedback in non-stationary multi-armed bandits, where the availability of reward feedback is restricted. We propose the first prior-free algorithm - that is, one that does not require prior knowledge of the degree of non-stationarity - that achieves near-optimal dynamic regret in this setting. Specifically, our algorithm attains a dynamic regret of $\tilde{\mathcal{O}}({K^{1/3} V_T^{1/3} T }/{ B^{1/3}})$, where $T$ is the number of rounds, $K$ is the number of arms, $B$ is the query budget, and $V_T$ is the variation budget capturing the degree of non-stationarity.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15073
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits
Li, Shaoang
Li, Jian
Machine Learning
Non-stationary multi-armed bandits enable agents to adapt to changing environments by incorporating mechanisms to detect and respond to shifts in reward distributions, making them well-suited for dynamic settings. However, existing approaches typically assume that reward feedback is available at every round - an assumption that overlooks many real-world scenarios where feedback is limited. In this paper, we take a significant step forward by introducing a new model of constrained feedback in non-stationary multi-armed bandits, where the availability of reward feedback is restricted. We propose the first prior-free algorithm - that is, one that does not require prior knowledge of the degree of non-stationarity - that achieves near-optimal dynamic regret in this setting. Specifically, our algorithm attains a dynamic regret of $\tilde{\mathcal{O}}({K^{1/3} V_T^{1/3} T }/{ B^{1/3}})$, where $T$ is the number of rounds, $K$ is the number of arms, $B$ is the query budget, and $V_T$ is the variation budget capturing the degree of non-stationarity.
title Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits
topic Machine Learning
url https://arxiv.org/abs/2509.15073