arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05019cs.LG
收藏

通过回归实现约束上下文老虎机的简单简化方案

A Simple Reduction Scheme for Constrained Contextual Bandits with Adversarial Contexts via Regression

Indian Institute of Technology Kharagpur(印度理工学院克勒格布尔分校);Tata Institute of Fundamental Research(塔塔基础研究院)

Dhruv Sarkar, Abhishek Sinha

AI总结:

本文提出了一种通过回归将约束上下文老虎机问题简化为无约束问题的方法,适用于对抗性上下文设置,并提供了改进的保证和透明的分析。

摘要:

我们研究了具有对抗性选择的约束上下文老虎机(CCB)问题,其中每个动作产生随机奖励并产生随机成本。我们采用标准的可实现性假设:在观察到的上下文中,奖励和成本独立地从固定分布中抽取,其期望值属于已知的功能类。我们考虑连续设置,即算法在预算耗尽后仍持续运行整个时间跨度。在此设置中,目标是同时控制遗憾和累积约束违规。基于Foster等人(2018)的开创性SquareCB框架,我们提出了一种简单且模块化的算法方案,利用在线回归预言机将约束问题简化为具有自适应定义替代奖励函数的标准无约束上下文老虎机问题。与大多数针对随机上下文的CCB工作不同,我们的简化在更一般的对抗性上下文设置中提供了改进的保证,并具有紧凑且透明的分析。

英文摘要:

We study constrained contextual bandits (CCB) with adversarially chosen contexts, where each action yields a random reward and incurs a random cost. We adopt the standard realizability assumption: conditioned on the observed context, rewards and costs are drawn independently from fixed distributions whose expectations belong to known function classes. We consider the continuing setting, in which the algorithm operates over the entire horizon even after the budget is exhausted. In this setting, the objective is to simultaneously control regret and cumulative constraint violation. Building on the seminal SquareCB framework of Foster et al. (2018), we propose a simple and modular algorithmic scheme that leverages online regression oracles to reduce the constrained problem to a standard unconstrained contextual bandit problem with adaptively defined surrogate reward functions. In contrast to most prior work on CCB, which focuses on stochastic contexts, our reduction yields improved guarantees for the more general adversarial context setting, together with a compact and transparent analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑