中文
相关论文

相关论文: A Closer Look at Small-loss Bounds for Bandits wit…

200 篇论文

We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all…

机器学习 · 计算机科学 2026-05-08 Harin Lee , Min-hwan Oh

We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based…

机器学习 · 统计学 2015-06-30 Junpei Komiyama , Junya Honda , Hisashi Kashima , Hiroshi Nakagawa

We consider regret minimization in a general collaborative multi-agent multi-armed bandit model, in which each agent faces a finite set of arms and may communicate with other agents through a central controller. The optimal arm for each…

机器学习 · 计算机科学 2023-12-18 Amitis Shidani , Sattar Vakili

Learning from human feedback plays an important role in aligning generative models, such as large language models (LLM). However, the effectiveness of this approach can be influenced by adversaries, who may intentionally provide misleading…

机器学习 · 计算机科学 2025-11-13 Qiwei Di , Jiafan He , Quanquan Gu

We study the problem of adversarial combinatorial bandit with a switching cost $\lambda$ for a switch of each selected arm in each round, considering both the bandit feedback and semi-bandit feedback settings. In the oblivious adversarial…

机器学习 · 统计学 2024-04-03 Yanyan Dong , Vincent Y. F. Tan

We present an efficient algorithm for linear contextual bandits with adversarial losses and stochastic action sets. Our approach reduces this setting to misspecification-robust adversarial linear bandits with fixed action sets. Without…

机器学习 · 计算机科学 2025-12-16 Tim van Erven , Jack Mayo , Julia Olkhovskaya , Chen-Yu Wei

In this paper, we investigate the stochastic contextual bandit with general function space and graph feedback. We propose an algorithm that addresses this problem by adapting to both the underlying graph structures and reward gaps. To the…

机器学习 · 计算机科学 2024-01-09 Xueping Gong , Jiheng Zhang

We study the regret in stochastic Multi-Armed Bandits (MAB) with multiple agents that communicate over an arbitrary connected communication graph. We analyzed a variant of Cooperative Successive Elimination algorithm, COOP-SE, and show an…

机器学习 · 计算机科学 2026-02-04 Idan Barnea , Tal Lancewicki , Yishay Mansour

In this paper, we investigate the streaming bandits problem, wherein the learner aims to minimize regret by dealing with online arriving arms and sublinear arm memory. We establish the tight worst-case regret lower bound of $\Omega \left(…

机器学习 · 计算机科学 2023-06-14 Shaoang Li , Lan Zhang , Junhao Wang , Xiang-Yang Li

In online learning problems, exploiting low variance plays an important role in obtaining tight performance guarantees yet is challenging because variances are often not known a priori. Recently, considerable progress has been made by Zhang…

机器学习 · 统计学 2023-02-07 Yeoneung Kim , Insoon Yang , Kwang-Sung Jun

We study the problem of information sharing and cooperation in Multi-Player Multi-Armed bandits. We propose the first algorithm that achieves logarithmic regret for this problem when the collision reward is unknown. Our results are based on…

机器学习 · 计算机科学 2022-10-04 Aldo Pacchiano , Peter Bartlett , Michael I. Jordan

In (online) learning theory the concepts of sparsity, variance and curvature are well-understood and are routinely used to obtain refined regret and generalization bounds. In this paper we further our understanding of these concepts in the…

机器学习 · 计算机科学 2017-11-06 Sébastien Bubeck , Michael B. Cohen , Yuanzhi Li

Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqrt{T}$-type regret in the unregularized setting. However, the…

机器学习 · 计算机科学 2026-03-03 Kaixuan Ji , Qingyue Zhao , Heyang Zhao , Qiwei Di , Quanquan Gu

We study how the regret guarantees of nonstochastic multi-armed bandits can be improved, if the effective range of the losses in each round is small (e.g. the maximal difference between two losses in a given round). Despite a recent…

机器学习 · 计算机科学 2020-01-03 Nicolò Cesa-Bianchi , Ohad Shamir

In this paper, we study the online shortest path problem in directed acyclic graphs (DAGs) under bandit feedback against an adaptive adversary. Given a DAG $G = (V, E)$ with a source node $v_{\mathsf{s}}$ and a sink node $v_{\mathsf{t}}$,…

机器学习 · 计算机科学 2025-04-04 Arnab Maiti , Zhiyuan Fan , Kevin Jamieson , Lillian J. Ratliff , Gabriele Farina

We consider a bandit problem where the buget is smaller than the number of arms, which may be infinite. In this regime, the usual objective in the literature is to minimize simple regret. To analyze broad classes of distributions with…

统计理论 · 数学 2025-11-04 Emmanuel Pilliat

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…

机器学习 · 计算机科学 2025-09-19 Shaoang Li , Jian Li

In multi-objective decision-making with hierarchical preferences, lexicographic bandits provide a natural framework for optimizing multiple objectives in a prioritized order. In this setting, a learner repeatedly selects arms and observes…

机器学习 · 计算机科学 2025-11-11 Bo Xue , Yuanyu Wan , Zhichao Lu , Qingfu Zhang

We provide new lower bounds on the regret that must be suffered by adversarial bandit algorithms. The new results show that recent upper bounds that either (a) hold with high-probability or (b) depend on the total lossof the best arm or (c)…

统计理论 · 数学 2017-02-28 Sébastien Gerchinovitz , Tor Lattimore

Optimal regret bounds for Multi-Armed Bandit problems are now well documented. They can be classified into two categories based on the growth rate with respect to the time horizon $T$: (i) small, distribution-dependent, bounds of order of…

数据结构与算法 · 计算机科学 2017-04-12 Arthur Flajolet , Patrick Jaillet