English
Related papers

Related papers: Generalized Policy Elimination: an efficient algor…

200 papers

We consider a multi-armed bandit problem where payoffs are a linear function of an observed stochastic contextual variable. In the scenario where there exists a gap between optimal and suboptimal rewards, several algorithms have been…

Data Structures and Algorithms · Computer Science 2014-07-08 José Bento , Stratis Ioannidis , S. Muthukrishnan , Jinyun Yan

The problem of opportunistic spectrum access in cognitive radio networks has been recently formulated as a non-Bayesian restless multi-armed bandit problem. In this problem, there are N arms (corresponding to channels) and one player…

Machine Learning · Computer Science 2011-11-10 Wenhan Dai , Yi Gai , Bhaskar Krishnamachari

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

In this paper, we investigate the existence of online learning algorithms with bandit feedback that simultaneously guarantee $O(1)$ regret compared to a given comparator strategy, and $\tilde{O}(\sqrt{T})$ regret compared to any fixed…

Machine Learning · Computer Science 2025-06-05 Adrian Müller , Jon Schneider , Stratis Skoulakis , Luca Viano , Volkan Cevher

We consider the problem of finitely parameterized multi-armed bandits where the model of the underlying stochastic environment can be characterized based on a common unknown parameter. The true parameter is unknown to the learning agent.…

Machine Learning · Computer Science 2020-11-10 Kishan Panaganti , Dileep Kalathil

Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. Yet, so far, such methods have been mostly analyzed from an optimization perspective, without addressing the problem of…

Machine Learning · Computer Science 2020-06-19 Yonathan Efroni , Lior Shani , Aviv Rosenberg , Shie Mannor

Online model selection in Bayesian bandits raises a fundamental exploration challenge: When an environment instance is sampled from a prior distribution, how can we design an adaptive strategy that explores multiple bandit learners and…

Machine Learning · Computer Science 2026-02-23 Aida Afshar , Yuke Zhang , Aldo Pacchiano

Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the…

Machine Learning · Computer Science 2012-07-03 Raman Arora , Ofer Dekel , Ambuj Tewari

Bandits with feedback graphs are powerful online learning models that interpolate between the full information and classic bandit problems, capturing many real-life applications. A recent work by Zhang et al. (2023) studies the contextual…

Machine Learning · Computer Science 2024-02-14 Mengxiao Zhang , Yuheng Zhang , Haipeng Luo , Paul Mineiro

We develop a general theory to optimize the frequentist regret for sequential learning problems, where efficient bandit and reinforcement learning algorithms can be derived from unified Bayesian principles. We propose a novel optimization…

Machine Learning · Computer Science 2024-02-12 Yunbei Xu , Assaf Zeevi

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

We consider the kernelized contextual bandit problem with a large feature space. This problem involves $K$ arms, and the goal of the forecaster is to maximize the cumulative rewards through learning the relationship between the contexts and…

Machine Learning · Statistics 2025-05-21 Shogo Iwazaki , Junpei Komiyama , Masaaki Imaizumi

Reward-biased maximum likelihood estimation (RBMLE) is a classic principle in the adaptive control literature for tackling explore-exploit trade-offs. This paper studies the stochastic contextual bandit problem with general bounded reward…

Machine Learning · Computer Science 2022-05-31 Yu-Heng Hung , Ping-Chun Hsieh

We study the stochastic contextual bandit with knapsacks (CBwK) problem, where each action, taken upon a context, not only leads to a random reward but also costs a random resource consumption in a vector form. The challenge is to maximize…

Machine Learning · Computer Science 2023-02-23 Yuxuan Han , Jialin Zeng , Yang Wang , Yang Xiang , Jiheng Zhang

We study the performance guarantees of exploration-free greedy algorithms for the linear contextual bandit problem. We introduce a novel condition, named the \textit{Local Anti-Concentration} (LAC) condition, which enables a greedy bandit…

Machine Learning · Statistics 2025-01-17 Seok-Jin Kim , Min-hwan Oh

We study online reinforcement learning in linear Markov decision processes with adversarial losses and bandit feedback, without prior knowledge on transitions or access to simulators. We introduce two algorithms that achieve improved regret…

Machine Learning · Computer Science 2023-10-19 Haolin Liu , Chen-Yu Wei , Julian Zimmert

We study the optimal batch-regret tradeoff for batch linear contextual bandits. For any batch number $M$, number of actions $K$, time horizon $T$, and dimension $d$, we provide an algorithm and prove its regret guarantee, which, due to…

Machine Learning · Computer Science 2022-10-18 Zihan Zhang , Xiangyang Ji , Yuan Zhou

The paper considers the problem of global optimization in the setup of stochastic process bandits. We introduce an UCB algorithm which builds a cascade of discretization trees based on generic chaining in order to render possible his…

Machine Learning · Statistics 2016-02-22 Emile Contal , Nicolas Vayatis

We investigate the \emph{linear contextual bandit problem} with independent and identically distributed (i.i.d.) contexts. In this problem, we aim to develop a \emph{Best-of-Both-Worlds} (BoBW) algorithm with regret upper bounds in both…

Machine Learning · Computer Science 2025-05-29 Masahiro Kato , Shinji Ito

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While…

Machine Learning · Computer Science 2020-10-08 Dylan J. Foster , Alexander Rakhlin , David Simchi-Levi , Yunzong Xu