Saved in:
Bibliografiske detaljer
Main Authors: Tsuchiya, Taira, Ito, Shinji, Honda, Junya
Format: Preprint
Udgivet: 2024
Fag:
Online adgang:https://arxiv.org/abs/2402.08321
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!
_version_ 1866909494860054528
author Tsuchiya, Taira
Ito, Shinji
Honda, Junya
author_facet Tsuchiya, Taira
Ito, Shinji
Honda, Junya
contents Partial monitoring is a generic framework of online decision-making problems with limited feedback. To make decisions from such limited feedback, it is necessary to find an appropriate distribution for exploration. Recently, a powerful approach for this purpose, \emph{exploration by optimization} (ExO), was proposed, which achieves optimal bounds in adversarial environments with follow-the-regularized-leader for a wide range of online decision-making problems. However, a naive application of ExO in stochastic environments significantly degrades regret bounds. To resolve this issue in locally observable games, we first establish a new framework and analysis for ExO with a hybrid regularizer. This development allows us to significantly improve existing regret bounds of best-of-both-worlds (BOBW) algorithms, which achieves nearly optimal bounds both in stochastic and adversarial environments. In particular, we derive a stochastic regret bound of $O(\sum_{a \neq a^*} k^2 m^2 \log T / Δ_a)$, where $k$, $m$, and $T$ are the numbers of actions, observations and rounds, $a^*$ is an optimal action, and $Δ_a$ is the suboptimality gap for action $a$. This bound is roughly $Θ(k^2 \log T)$ times smaller than existing BOBW bounds. In addition, for globally observable games, we provide a new BOBW algorithm with the first $O(\log T)$ stochastic bound.
format Preprint
id arxiv_https___arxiv_org_abs_2402_08321
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
Tsuchiya, Taira
Ito, Shinji
Honda, Junya
Machine Learning
Partial monitoring is a generic framework of online decision-making problems with limited feedback. To make decisions from such limited feedback, it is necessary to find an appropriate distribution for exploration. Recently, a powerful approach for this purpose, \emph{exploration by optimization} (ExO), was proposed, which achieves optimal bounds in adversarial environments with follow-the-regularized-leader for a wide range of online decision-making problems. However, a naive application of ExO in stochastic environments significantly degrades regret bounds. To resolve this issue in locally observable games, we first establish a new framework and analysis for ExO with a hybrid regularizer. This development allows us to significantly improve existing regret bounds of best-of-both-worlds (BOBW) algorithms, which achieves nearly optimal bounds both in stochastic and adversarial environments. In particular, we derive a stochastic regret bound of $O(\sum_{a \neq a^*} k^2 m^2 \log T / Δ_a)$, where $k$, $m$, and $T$ are the numbers of actions, observations and rounds, $a^*$ is an optimal action, and $Δ_a$ is the suboptimality gap for action $a$. This bound is roughly $Θ(k^2 \log T)$ times smaller than existing BOBW bounds. In addition, for globally observable games, we provide a new BOBW algorithm with the first $O(\log T)$ stochastic bound.
title Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
topic Machine Learning
url https://arxiv.org/abs/2402.08321