English
Related papers

Related papers: Explore-then-Commit for Nonstationary Linear Bandi…

200 papers

Multi-armed bandit problems are considered as a paradigm of the trade-off between exploring the environment to find profitable actions and exploiting what is already known. In the stationary case, the distributions of the rewards do not…

Statistics Theory · Mathematics 2008-12-18 Aurélien Garivier , Eric Moulines

This paper studies the problem of designing an optimal sequence of interventions in a causal graphical model to minimize cumulative regret with respect to the best intervention in hindsight. This is, naturally, posed as a causal bandit…

Machine Learning · Statistics 2023-04-04 Burak Varici , Karthikeyan Shanmugam , Prasanna Sattigeri , Ali Tajer

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

We study the piecewise stationary combinatorial semi-bandit problem with causally related rewards. In our nonstationary environment, variations in the base arms' distributions, causal relationships between rewards, or both, change the…

Machine Learning · Computer Science 2023-07-27 Behzad Nourani-Koliji , Steven Bilaj , Amir Rezaei Balef , Setareh Maghsudi

We study a class of adversarial bandit optimization problems in which the loss functions may be non-convex and non-smooth. In each round, the learner observes a loss that consists of an underlying linear component together with an…

Machine Learning · Computer Science 2026-03-30 Zhuoyu Cheng , Kohei Hatano , Eiji Takimoto

Contextual bandits are a central framework for sequential decision-making, with applications ranging from recommendation systems to clinical trials. While nonparametric methods can flexibly model complex reward structures, they suffer from…

Statistics Theory · Mathematics 2026-01-01 Wanteng Ma , T. Tony Cai

Modifying the reward-biased maximum likelihood method originally proposed in the adaptive control literature, we propose novel learning algorithms to handle the explore-exploit trade-off in linear bandits problems as well as generalized…

Machine Learning · Computer Science 2020-10-09 Yu-Heng Hung , Ping-Chun Hsieh , Xi Liu , P. R. Kumar

We study linear bandits when the underlying reward function is not linear. Existing work relies on a uniform misspecification parameter $\epsilon$ that measures the sup-norm error of the best linear approximation. This results in an…

Machine Learning · Computer Science 2023-07-21 Chong Liu , Ming Yin , Yu-Xiang Wang

In this work, we investigate the problem of adapting to the presence or absence of causal structure in multi-armed bandit problems. In addition to the usual reward signal, we assume the learner has access to additional variables, observed…

Machine Learning · Computer Science 2024-07-02 Ziyi Liu , Idan Attias , Daniel M. Roy

We consider the problem of learning in episodic finite-horizon Markov decision processes with an unknown transition function, bandit feedback, and adversarial losses. We propose an efficient algorithm that achieves…

Machine Learning · Computer Science 2020-11-03 Chi Jin , Tiancheng Jin , Haipeng Luo , Suvrit Sra , Tiancheng Yu

In this study, we explore a collaborative multi-agent stochastic linear bandit setting involving a network of $N$ agents that communicate locally to minimize their collective regret while keeping their expected cost under a specified…

Machine Learning · Computer Science 2024-10-24 Amirhossein Afsharrad , Parisa Oftadeh , Ahmadreza Moradipari , Sanjay Lall

Tree-form sequential decision making (TFSDM) extends classical one-shot decision making by modeling tree-form interactions between an agent and a potentially adversarial environment. It captures the online decision-making problems that each…

Computer Science and Game Theory · Computer Science 2021-03-09 Gabriele Farina , Robin Schmucker , Tuomas Sandholm

We study a two-player zero-sum game in which the row player aims to maximize their payoff against a competing column player, under an unknown payoff matrix estimated through bandit feedback. We propose three algorithms based on the…

Machine Learning · Computer Science 2026-02-20 Elif Yılmaz , Christos Dimitrakakis

In this paper, we study the MNL-Bandit problem in a non-stationary environment and present an algorithm with a worst-case expected regret of $\tilde{O}\left( \min \left\{ \sqrt{NTL}\;,\; N^{\frac{1}{3}}(\Delta_{\infty}^{K})^{\frac{1}{3}}…

Machine Learning · Computer Science 2023-06-05 Ayoub Foussoul , Vineet Goyal , Varun Gupta

Contextual multi-armed bandit (MAB) algorithms have been shown promising for maximizing cumulative rewards in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health.…

Machine Learning · Statistics 2019-02-01 Gi-Soo Kim , Myunghee Cho Paik

Boltzmann exploration is a classic strategy for sequential decision-making under uncertainty, and is one of the most standard tools in Reinforcement Learning (RL). Despite its widespread use, there is virtually no theoretical understanding…

Machine Learning · Computer Science 2017-11-08 Nicolò Cesa-Bianchi , Claudio Gentile , Gábor Lugosi , Gergely Neu

We consider a combinatorial generalization of the classical multi-armed bandit problem that is defined as follows. There is a given bipartite graph of $M$ users and $N \geq M$ resources. For each user-resource pair $(i,j)$, there is an…

Optimization and Control · Mathematics 2015-03-17 Yi Gai , Bhaskar Krishnamachari , Mingyan Liu

We study the online restless bandit problem, where the state of each arm evolves according to a Markov chain, and the reward of pulling an arm depends on both the pulled arm and the current state of the corresponding Markov chain. In this…

Machine Learning · Computer Science 2020-11-09 Siwei Wang , Longbo Huang , John C. S. Lui

We study the greedy (exploitation-only) algorithm in bandit problems with a known reward structure. We allow arbitrary finite reward structures, while prior work focused on a few specific ones. We fully characterize when the greedy…

Machine Learning · Computer Science 2025-11-10 Aleksandrs Slivkins , Yunzong Xu , Shiliang Zuo

Many important optimization problems, such as the minimum spanning tree and minimum-cost flow, can be solved optimally by a greedy method. In this work, we study a learning variant of these problems, where the model of the problem is…

Machine Learning · Computer Science 2014-11-24 Branislav Kveton , Zheng Wen , Azin Ashkan , Michal Valko