English
Related papers

Related papers: Logarithmic Regret for Online KL-Regularized Reinf…

200 papers

We study bandit model selection in stochastic environments. Our approach relies on a meta-algorithm that selects between candidate base algorithms. We develop a meta-algorithm-base algorithm abstraction that can work with general classes of…

Machine Learning · Computer Science 2022-12-06 Aldo Pacchiano , My Phan , Yasin Abbasi-Yadkori , Anup Rao , Julian Zimmert , Tor Lattimore , Csaba Szepesvari

In the stochastic contextual low-rank matrix bandit problem, the expected reward of an action is given by the inner product between the action's feature matrix and some fixed, but initially unknown $d_1$ by $d_2$ matrix $\Theta^*$ with rank…

Machine Learning · Statistics 2024-01-17 Yue Kang , Cho-Jui Hsieh , Thomas C. M. Lee

Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions. For example, given a classifier that determines loan approval based on credit scores, applicants may open…

Machine Learning · Computer Science 2026-02-09 Chase Hutton , Adam Melrod , Han Shao

In many real-world applications, it is hard to provide a reward signal in each step of a Reinforcement Learning (RL) process and more natural to give feedback when an episode ends. To this end, we study the recently proposed model of RL…

Machine Learning · Computer Science 2024-05-15 Asaf Cassel , Haipeng Luo , Aviv Rosenberg , Dmitry Sotnikov

We study algorithms for online linear optimization in Hilbert spaces, focusing on the case where the player is unconstrained. We develop a novel characterization of a large class of minimax algorithms, recovering, and even improving,…

Machine Learning · Computer Science 2014-05-22 H. Brendan McMahan , Francesco Orabona

We present an efficient second-order algorithm with $\tilde{O}(\frac{1}{\eta}\sqrt{T})$ regret for the bandit online multiclass problem. The regret bound holds simultaneously with respect to a family of loss functions parameterized by…

Machine Learning · Computer Science 2018-01-19 Alina Beygelzimer , Francesco Orabona , Chicheng Zhang

Kullback-Leibler (KL) regularization is widely used in offline decision-making and offers several benefits, motivating recent work on the sample complexity of offline learning with respect to KL-regularized performance metrics.…

Machine Learning · Computer Science 2026-05-05 Kaixuan Ji , Qiwei Di , Heyang Zhao , Qingyue Zhao , Quanquan Gu

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

This paper investigates a hybrid learning framework for reinforcement learning (RL) in which the agent can leverage both an offline dataset and online interactions to learn the optimal policy. We present a unified algorithm and analysis and…

Machine Learning · Computer Science 2025-07-01 Ruiquan Huang , Donghao Li , Chengshuai Shi , Cong Shen , Jing Yang

Reinforcement learning utilizing kernel ridge regression to predict the expected value function represents a powerful method with great representational capacity. This setting is a highly versatile framework amenable to analytical results.…

Machine Learning · Computer Science 2024-11-01 Sattar Vakili , Julia Olkhovskaya

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

We study stochastic linear optimization problem with bandit feedback. The set of arms take values in an $N$-dimensional space and belong to a bounded polyhedron described by finitely many linear inequalities. We provide a lower bound for…

Machine Learning · Computer Science 2015-09-29 Manjesh K. Hanawal , Amir Leshem , Venkatesh Saligrama

We investigate the online bandit learning of the monotone multi-linear DR-submodular functions, designing the algorithm $\mathtt{BanditMLSM}$ that attains $O(T^{2/3}\log T)$ of $(1-1/e)$-regret. Then we reduce submodular bandit with…

Machine Learning · Computer Science 2023-05-23 Zongqi Wan , Jialin Zhang , Wei Chen , Xiaoming Sun , Zhijie Zhang

We study a new type of K-armed bandit problem where the expected return of one arm may depend on the returns of other arms. We present a new algorithm for this general class of problems and show that under certain circumstances it is…

Machine Learning · Computer Science 2014-11-12 Tor Lattimore , Remi Munos

We study online meta-learning with bandit feedback, with the goal of improving performance across multiple tasks if they are similar according to some natural similarity measure. As the first to target the adversarial online-within-online…

Machine Learning · Computer Science 2023-11-02 Mikhail Khodak , Ilya Osadchiy , Keegan Harris , Maria-Florina Balcan , Kfir Y. Levy , Ron Meir , Zhiwei Steven Wu

We investigate multiarmed bandits with delayed feedback, where the delays need neither be identical nor bounded. We first prove that "delayed" Exp3 achieves the $O(\sqrt{(KT + D)\ln K} )$ regret bound conjectured by Cesa-Bianchi et al.…

Machine Learning · Computer Science 2019-11-20 Tobias Sommer Thune , Nicolò Cesa-Bianchi , Yevgeny Seldin

Online structured prediction is a task of sequentially predicting outputs with complex structures based on inputs and past observations, encompassing online classification. Recent studies showed that in the full-information setting, we can…

Machine Learning · Computer Science 2026-01-06 Yuki Shibukawa , Taira Tsuchiya , Shinsaku Sakaue , Kenji Yamanishi

We study the problem of \emph{dynamic regret minimization} in $K$-armed Dueling Bandits under non-stationary or time varying preferences. This is an online learning setup where the agent chooses a pair of items at each round and observes…

Machine Learning · Computer Science 2022-06-14 Aadirupa Saha , Shubham Gupta

We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require carefully constructing optimistic and biased loss…

Machine Learning · Computer Science 2020-11-02 Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei , Mengxiao Zhang

We address the problem of learning in an online, bandit setting where the learner must repeatedly select among $K$ actions, but only receives partial feedback based on its choices. We establish two new facts: First, using a new algorithm…

Machine Learning · Computer Science 2011-10-28 Alina Beygelzimer , John Langford , Lihong Li , Lev Reyzin , Robert E. Schapire