English
Related papers

Related papers: A Diffusion Analysis of Policy Gradient for Stocha…

200 papers

A sensing policy for the restless multi-armed bandit problem with stationary but unknown reward distributions is proposed. The work is presented in the context of cognitive radios in which the bandit problem arises when deciding which parts…

Information Theory · Computer Science 2012-11-20 Jan Oksanen , Visa Koivunen , H. Vincent Poor

We introduce a novel online learning framework that unifies and generalizes pre-established models, such as delayed and corrupted feedback, to encompass adversarial environments where action feedback evolves over time. In this setting, the…

Machine Learning · Computer Science 2024-05-28 Yogev Bar-On , Yishay Mansour

This is a short communication on a Lyapunov function argument for softmax in bandit problems. There are a number of excellent papers coming out using differential equations for policy gradient algorithms in reinforcement learning…

Machine Learning · Computer Science 2020-07-21 Neil Walton

We consider a situation where an agent has $T$ ressources to be allocated to a larger number $N$ of actions. Each action can be completed at most once and results in a stochastic reward with unknown mean. The goal of the agent is to…

Statistics Theory · Mathematics 2020-11-04 Solenne Gaucher

We consider the problem of stochastic $K$-armed dueling bandit in the contextual setting, where at each round the learner is presented with a context set of $K$ items, each represented by a $d$-dimensional feature vector, and the goal of…

Machine Learning · Computer Science 2021-05-11 Aadirupa Saha , Aditya Gopalan

Motivated by recommendation problems in music streaming platforms, we propose a nonstationary stochastic bandit model in which the expected reward of an arm depends on the number of rounds that have passed since the arm was last pulled.…

Machine Learning · Statistics 2020-02-20 Leonardo Cella , Nicolò Cesa-Bianchi

Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributions and prove a…

Machine Learning · Computer Science 2019-10-15 Young Hun Jung , Marc Abeille , Ambuj Tewari

This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least…

Machine Learning · Statistics 2011-07-26 Antoine Salomon , Jean-Yves Audibert

We study the dynamic regret of multi-armed bandit and experts problem in non-stationary stochastic environments. We introduce a new parameter $\Lambda$, which measures the total statistical variance of the loss distributions over $T$ rounds…

Machine Learning · Computer Science 2019-06-24 Chen-Yu Wei , Yi-Te Hong , Chi-Jen Lu

We study stochastic decision-theoretic online learning with full information and event-level pure differential privacy. A COLT open problem of Hu and Mehta asks to determine the optimal gap-dependent regret rate for stochastic…

Machine Learning · Computer Science 2026-05-29 Tommaso Cesari , Roberto Colomboni

We derive an online learning algorithm with improved regret guarantees for `easy' loss sequences. We consider two types of `easiness': (a) stochastic loss sequences and (b) adversarial loss sequences with small effective range of the…

Machine Learning · Computer Science 2019-08-28 Tobias Sommer Thune , Yevgeny Seldin

We study a variation of the classical multi-armed bandits problem. In this problem, the learner has to make a sequence of decisions, picking from a fixed set of choices. In each round, she receives as feedback only the loss incurred from…

Machine Learning · Computer Science 2017-09-18 Paresh Nakhe , Rebecca Reiffenhäuser

Most contextual bandit algorithms minimize regret against the best fixed policy, a questionable benchmark for non-stationary environments that are ubiquitous in applications. In this work, we develop several efficient contextual bandit…

Machine Learning · Computer Science 2019-04-05 Haipeng Luo , Chen-Yu Wei , Alekh Agarwal , John Langford

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…

Machine Learning · Computer Science 2026-03-03 Kaixuan Ji , Qingyue Zhao , Heyang Zhao , Qiwei Di , Quanquan Gu

We study how representation learning can improve the efficiency of bandit problems. We study the setting where we play $T$ linear bandits with dimension $d$ concurrently, and these $T$ bandit tasks share a common $k (\ll d)$ dimensional…

Machine Learning · Computer Science 2021-05-06 Jiaqi Yang , Wei Hu , Jason D. Lee , Simon S. Du

We study a variant of the stochastic linear bandit problem wherein we optimize a linear objective function but rewards are accrued only orthogonal to an unknown subspace (which we interpret as a \textit{protected space}) given only…

Machine Learning · Computer Science 2021-03-03 Advait Parulekar , Soumya Basu , Aditya Gopalan , Karthikeyan Shanmugam , Sanjay Shakkottai

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Machine Learning · Computer Science 2021-01-07 Branislav Kveton , Martin Mladenov , Chih-Wei Hsu , Manzil Zaheer , Csaba Szepesvari , Craig Boutilier

We study a sequential decision problem where the learner faces a sequence of $K$-armed bandit tasks. The task boundaries might be known (the bandit meta-learning setting), or unknown (the non-stationary bandit setting). For a given integer…

We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions, where states are scalar-valued and running control rewards are absent but volatilities of the state processes depend…

Machine Learning · Computer Science 2025-07-25 Yilie Huang , Yanwei Jia , Xun Yu Zhou

Motivated by practical needs such as large-scale learning, we study the impact of adaptivity constraints to linear contextual bandits, a central problem in online active learning. We consider two popular limited adaptivity models in…

Machine Learning · Computer Science 2021-04-26 Yufei Ruan , Jiaqi Yang , Yuan Zhou