English
Related papers

Related papers: Regret Bounds for Adversarial Contextual Bandits w…

200 papers

We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all…

Machine Learning · Computer Science 2026-05-08 Harin Lee , Min-hwan Oh

We consider a contextual bandit problem with $S$ contexts and $K$ actions. In each round $t=1,2,\dots$, the learner observes a random context and chooses an action based on its past experience. The learner then observes a random reward…

Machine Learning · Computer Science 2023-11-29 Chung-Wei Lee , Qinghua Liu , Yasin Abbasi-Yadkori , Chi Jin , Tor Lattimore , Csaba Szepesvári

Despite the significant interest and progress in reinforcement learning (RL) problems with adversarial corruption, current works are either confined to the linear setting or lead to an undesired $\tilde{O}(\sqrt{T}\zeta)$ regret bound,…

Machine Learning · Statistics 2024-02-13 Chenlu Ye , Wei Xiong , Quanquan Gu , Tong Zhang

We derive near-optimal per-action regret bounds for sleeping bandits, in which both the sets of available arms and their losses in every round are chosen by an adversary. In a setting with $K$ total arms and at most $A$ available arms in…

Machine Learning · Computer Science 2024-05-31 Quan Nguyen , Nishant A. Mehta

We consider the adversarial linear contextual bandit setting, which allows for the loss functions associated with each of $K$ arms to change over time without restriction. Assuming the $d$-dimensional contexts are drawn from a fixed known…

Machine Learning · Computer Science 2023-05-25 Julia Olkhovskaya , Jack Mayo , Tim van Erven , Gergely Neu , Chen-Yu Wei

We study reinforcement learning with linear function approximation and adversarially changing cost functions, a setup that has mostly been considered under simplifying assumptions such as full information feedback or exploratory…

Machine Learning · Computer Science 2023-01-31 Uri Sherman , Tomer Koren , Yishay Mansour

Recent advances in Reinforcement Learning from Human Feedback (RLHF) have shown that KL-regularization plays a pivotal role in improving the efficiency of RL fine-tuning for large language models (LLMs). Despite its empirical advantage, the…

Machine Learning · Computer Science 2026-03-12 Heyang Zhao , Chenlu Ye , Wei Xiong , Quanquan Gu , Tong Zhang

We consider the problem of Online Convex Optimization (OCO) with two-point bandit feedback. In this setting, a player attempts to minimize a sequence of adversarially generated convex loss functions, while only observing the value of each…

Machine Learning · Computer Science 2026-04-07 Haishan Ye

Nonparametric contextual bandit is an important model of sequential decision making problems. Under $\alpha$-Tsybakov margin condition, existing research has established a regret bound of $\tilde{O}\left(T^{1-\frac{\alpha+1}{d+2}}\right)$…

Machine Learning · Computer Science 2025-05-09 Puning Zhao , Rongfei Fan , Shaowei Wang , Li Shen , Qixin Zhang , Zong Ke , Tianhang Zheng

Conservative Contextual Bandits (CCBs) address safety in sequential decision making by requiring that an agent's policy, along with minimizing regret, also satisfies a safety constraint: the performance is not worse than a baseline policy…

Machine Learning · Computer Science 2024-12-10 Rohan Deb , Mohammad Ghavamzadeh , Arindam Banerjee

Fast changing states or volatile environments pose a significant challenge to online optimization, which needs to perform rapid adaptation under limited observation. In this paper, we give query and regret optimal bandit algorithms under…

Machine Learning · Computer Science 2024-01-18 Zhou Lu , Qiuyi Zhang , Xinyi Chen , Fred Zhang , David Woodruff , Elad Hazan

The cross-learning contextual bandit problem with graphical feedback has recently attracted significant attention. In this setting, there is a contextual bandit with a feedback graph over the arms, and pulling an arm reveals the loss for…

Machine Learning · Computer Science 2025-02-10 Ruiyuan Huang , Zengfeng Huang

We study the adversarial bandit problem with composite anonymous delayed feedback. In this setting, losses of an action are split into $d$ components, spreading over consecutive rounds after the action is chosen. And in each round, the…

Machine Learning · Computer Science 2022-04-29 Zongqi Wan , Xiaoming Sun , Jialin Zhang

In this paper, we study the contextual multinomial logit (MNL) bandit problem in which a learning agent sequentially selects an assortment based on contextual information, and user feedback follows an MNL choice model. There has been a…

Machine Learning · Statistics 2025-10-17 Joongkyu Lee , Min-hwan Oh

We develop a novel and generic algorithm for the adversarial multi-armed bandit problem (or more generally the combinatorial semi-bandit problem). When instantiated differently, our algorithm achieves various new data-dependent regret…

Machine Learning · Computer Science 2018-06-08 Chen-Yu Wei , Haipeng Luo

Computationally efficient contextual bandits are often based on estimating a predictive model of rewards given contexts and arms using past data. However, when the reward model is not well-specified, the bandit algorithm may incur…

Machine Learning · Computer Science 2021-06-14 Sanath Kumar Krishnamurthy , Vitor Hadad , Susan Athey

This paper proposes a linear bandit algorithm that is adaptive to environments at two different levels of hierarchy. At the higher level, the proposed algorithm adapts to a variety of types of environments. More precisely, it achieves…

Machine Learning · Computer Science 2023-02-27 Shinji Ito , Kei Takemura

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

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

We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed at the start of each episode. Performance is measured by cumulative regret against the…

Machine Learning · Computer Science 2026-05-18 Zijun Chen , Zihan Zhang