English
Related papers

Related papers: A UCB Bandit Algorithm for General ML-Based Estima…

200 papers

The upper confidence bound (UCB) policy is recognized as an order-optimal solution for the classical total-reward bandit problem. While similar UCB-based approaches have been applied to the max bandit problem, which aims to maximize the…

Machine Learning · Statistics 2024-11-04 Nobuaki Kikkawa , Hiroshi Ohno

We consider a stochastic multi-armed bandit setting and study the problem of constrained regret minimization over a given time horizon. Each arm is associated with an unknown, possibly multi-dimensional distribution, and the merit of an arm…

Machine Learning · Computer Science 2023-01-05 Anmol Kagrecha , Jayakrishnan Nair , Krishna Jagannathan

We consider what we call the offline-to-online learning setting, focusing on stochastic finite-armed bandit problems. In offline-to-online learning, a learner starts with offline data collected from interactions with an unknown environment…

Machine Learning · Computer Science 2025-03-11 Flore Sentenac , Ilbin Lee , Csaba Szepesvari

The contextual linear bandit is an important online learning problem where given arm features, a learning agent selects an arm at each round to maximize the cumulative rewards in the long run. A line of works, called the clustering of…

Machine Learning · Computer Science 2023-10-11 Zhiyong Wang , Jize Xie , Xutong Liu , Shuai Li , John C. S. Lui

In this paper we propose and explore the k-Nearest Neighbour UCB algorithm for multi-armed bandits with covariates. We focus on a setting where the covariates are supported on a metric space of low intrinsic dimension, such as a manifold…

Machine Learning · Computer Science 2018-03-02 Henry WJ Reeve , Joe Mellor , Gavin Brown

The exploration-exploitation dilemma has been a central challenge in reinforcement learning (RL) with complex model classes. In this paper, we propose a new algorithm, Monotonic Q-Learning with Upper Confidence Bound (MQL-UCB) for RL with…

Machine Learning · Computer Science 2025-10-06 Heyang Zhao , Jiafan He , Quanquan Gu

The multi-armed bandit problem has been extensively studied under the stationary assumption. However in reality, this assumption often does not hold because the distributions of rewards themselves may change over time. In this paper, we…

Machine Learning · Computer Science 2017-11-22 Fang Liu , Joohyun Lee , Ness Shroff

We characterize a joint CLT of the number of pulls and the sample mean reward of the arms in a stochastic two-armed bandit environment under UCB algorithms. Several implications of this result are in place: (1) a nonstandard CLT of the…

Machine Learning · Statistics 2025-03-10 Yilun Chen , Jiaqi Lu

Intrinsic rewards play a central role in handling the exploration-exploitation trade-off when designing sequential decision-making algorithms, in both foundational theory and state-of-the-art deep reinforcement learning. The LinUCB…

Machine Learning · Computer Science 2022-04-13 Jordan T. Ash , Cyril Zhang , Surbhi Goel , Akshay Krishnamurthy , Sham Kakade

Machine unlearning aims to unlearn data points from a learned model, offering a principled way to process data-deletion requests and mitigate privacy risks without full retraining. Prior work has mainly studied unsupervised / supervised…

Machine Learning · Computer Science 2026-05-04 Zichun Ye , Runqi Wang , Xuchuang Wang , Xutong Liu , Shuai Li , Mohammad Hajiesmaili

The analysis of online least squares estimation is at the heart of many stochastic sequential decision making problems. We employ tools from the self-normalized processes to provide a simple and self-contained proof of a tail bound of a…

Artificial Intelligence · Computer Science 2011-02-15 Yasin Abbasi-Yadkori , David Pal , Csaba Szepesvari

In this article, we introduce the concept of model confidence bounds (MCB) for variable selection in the context of nested models. Similarly to the endpoints in the familiar confidence interval for parameter estimation, the MCB identifies…

Methodology · Statistics 2018-07-27 Yang Li , Yuetian Luo , Davide Ferrari , Xiaonan Hu , Yichen Qin

We consider a resource-aware variant of the classical multi-armed bandit problem: In each round, the learner selects an arm and determines a resource limit. It then observes a corresponding (random) reward, provided the (random) amount of…

Machine Learning · Computer Science 2022-10-18 Viktor Bengs , Eyke Hüllermeier

We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minimax worst-case regret, but their gap-dependent bounds remain…

Machine Learning · Statistics 2025-10-09 Haochen Zhang , Zhong Zheng , Lingzhou Xue

I present the first algorithm for stochastic finite-armed bandits that simultaneously enjoys order-optimal problem-dependent regret and worst-case regret. Besides the theoretical results, the new algorithm is simple, efficient and…

Machine Learning · Computer Science 2016-02-25 Tor Lattimore

Many physical systems have underlying safety considerations that require that the strategy deployed ensures the satisfaction of a set of constraints. Further, often we have only partial information on the state of the system. We study the…

Machine Learning · Computer Science 2022-03-30 Jiabin Lin , Xian Yeow Lee , Talukder Jubery , Shana Moothedath , Soumik Sarkar , Baskar Ganapathysubramanian

Bayesian bandit algorithms with approximate Bayesian inference have been widely used in real-world applications. However, there is a large discrepancy between the superior practical performance of these approaches and their theoretical…

Machine Learning · Computer Science 2023-11-13 Ziyi Huang , Henry Lam , Amirhossein Meisami , Haofeng Zhang

I introduce and analyse an anytime version of the Optimally Confident UCB (OCUCB) algorithm designed for minimising the cumulative regret in finite-armed stochastic bandits with subgaussian noise. The new algorithm is simple, intuitive (in…

Machine Learning · Computer Science 2016-05-09 Tor Lattimore

Classic contextual bandit algorithms for linear models, such as LinUCB, assume that the reward distribution for an arm is modeled by a stationary linear regression. When the linear regression model is non-stationary over time, the regret of…

Machine Learning · Statistics 2020-02-14 Qin Ding , Cho-Jui Hsieh , James Sharpnack

This paper considers a multi-armed bandit (MAB) problem in which multiple mobile agents receive rewards by sampling from a collection of spatially dispersed stochastic processes, called bandits. The goal is to formulate a decentralized…

Machine Learning · Computer Science 2020-04-01 Pathmanathan Pankayaraj , D. H. S. Maithripala , J. M. Berg