English
Related papers

Related papers: Anti-Concentrated Confidence Bonuses for Scalable …

200 papers

We tackle the problem of online reward maximisation over a large finite set of actions described by their contexts. We focus on the case when the number of actions is too big to sample all of them even once. However we assume that we have…

Machine Learning · Computer Science 2013-09-27 Michal Valko , Nathaniel Korda , Remi Munos , Ilias Flaounas , Nelo Cristianini

In this paper we investigate the problem of stochastic multi-armed bandits (MAB) in the (local) differential privacy (DP/LDP) model. Unlike previous results that assume bounded/sub-Gaussian reward distributions, we focus on the setting…

Machine Learning · Computer Science 2022-03-25 Youming Tao , Yulian Wu , Peng Zhao , Di Wang

We study contextual bandits with nonlinear and path-dependent rewards through a novel signature-transform-based approach. Leveraging the universal nonlinearity property of signatures, we approximate continuous path-dependent reward…

Machine Learning · Computer Science 2026-05-12 Xin Guo , Grace He , Xinyu Li

We introduce in this paper a new algorithm for Multi-Armed Bandit (MAB) problems. A machine learning paradigm popular within Cognitive Network related topics (e.g., Spectrum Sensing and Allocation). We focus on the case where the rewards…

Machine Learning · Statistics 2012-04-10 Wassim Jouini , Christophe Moy

We propose a simple model selection approach for algorithms in stochastic bandit and reinforcement learning problems. As opposed to prior work that (implicitly) assumes knowledge of the optimal regret, we only require that each base…

Machine Learning · Computer Science 2020-12-25 Aldo Pacchiano , Christoph Dann , Claudio Gentile , Peter Bartlett

This paper considers contextual bandits with a finite number of arms, where the contexts are independent and identically distributed $d$-dimensional random vectors, and the expected rewards are linear in both the arm parameters and…

Machine Learning · Statistics 2025-05-07 Yanglei Song , Meng zhou

Safety is a desirable property that can immensely increase the applicability of learning algorithms in real-world decision-making problems. It is much easier for a company to deploy an algorithm that is safe, i.e., guaranteed to perform at…

Machine Learning · Statistics 2017-03-07 Abbas Kazerouni , Mohammad Ghavamzadeh , Yasin Abbasi-Yadkori , Benjamin Van Roy

We study the stochastic Budgeted Multi-Armed Bandit (MAB) problem, where a player chooses from $K$ arms with unknown expected rewards and costs. The goal is to maximize the total reward under a budget constraint. A player thus seeks to…

Machine Learning · Computer Science 2023-08-16 Marco Heyden , Vadim Arzamasov , Edouard Fouché , Klemens Böhm

We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting. We then apply it to study finite-time horizon stochastic control problems with linear dynamics but unknown coefficients and…

Machine Learning · Computer Science 2021-12-22 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang

We study reward maximisation in a wide class of structured stochastic multi-armed bandit problems, where the mean rewards of arms satisfy some given structural constraints, e.g. linear, unimodal, sparse, etc. Our aim is to develop methods…

Machine Learning · Statistics 2020-07-03 Rémy Degenne , Han Shao , Wouter M. Koolen

We study the corrupted bandit problem, i.e. a stochastic multi-armed bandit problem with $k$ unknown reward distributions, which are heavy-tailed and corrupted by a history-independent adversary or Nature. To be specific, the reward…

Machine Learning · Computer Science 2023-03-22 Debabrota Basu , Odalric-Ambrym Maillard , Timothée Mathieu

Recent works on neural contextual bandits have achieved compelling performances due to their ability to leverage the strong representation power of neural networks (NNs) for reward prediction. Many applications of contextual bandits involve…

Machine Learning · Computer Science 2023-03-02 Zhongxiang Dai , Yao Shu , Arun Verma , Flint Xiaofeng Fan , Bryan Kian Hsiang Low , Patrick Jaillet

Bandit problems with linear or concave reward have been extensively studied, but relatively few works have studied bandits with non-concave reward. This work considers a large family of bandit problems where the unknown underlying reward…

Machine Learning · Computer Science 2021-07-12 Baihe Huang , Kaixuan Huang , Sham M. Kakade , Jason D. Lee , Qi Lei , Runzhe Wang , Jiaqi Yang

In many real-world sequential decision-making problems, an action does not immediately reflect on the feedback and spreads its effects over a long time frame. For instance, in online advertising, investing in a platform produces an…

Machine Learning · Computer Science 2023-05-31 Marco Mussi , Alberto Maria Metelli , Marcello Restelli

In online reinforcement learning (RL), efficient exploration remains particularly challenging in high-dimensional environments with sparse rewards. In low-dimensional environments, where tabular parameterization is possible, count-based…

Machine Learning · Computer Science 2021-06-21 Tianjun Zhang , Paria Rashidinejad , Jiantao Jiao , Yuandong Tian , Joseph Gonzalez , Stuart Russell

We study the challenging exploration incentive problem in both bandit and reinforcement learning, where the rewards are scale-free and potentially unbounded, driven by real-world scenarios and differing from existing work. Past works in…

Machine Learning · Computer Science 2024-05-07 Mengfan Xu , Diego Klabjan

We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic…

Machine Learning · Computer Science 2023-11-02 Thodoris Lykouris , Max Simchowitz , Aleksandrs Slivkins , Wen Sun

We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under temporal drifts, ie, both the reward and state transition distributions are allowed to evolve over time, as long as their respective total…

Machine Learning · Computer Science 2020-05-19 Wang Chi Cheung , David Simchi-Levi , Ruihao Zhu

We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both…

Machine Learning · Computer Science 2022-03-25 Guojun Xiong , Jian Li , Rahul Singh

We propose a new bootstrap-based online algorithm for stochastic linear bandit problems. The key idea is to adopt residual bootstrap exploration, in which the agent estimates the next step reward by re-sampling the residuals of mean reward…

Machine Learning · Statistics 2022-06-20 Shuang Wu , Chi-Hua Wang , Yuantong Li , Guang Cheng