中文
相关论文

相关论文: Worst-Case Regret Bounds for Combinatorial Thompso…

200 篇论文

We study safe linear bandits (SLBs), where an agent selects actions from a convex set to maximize an unknown linear objective subject to unknown linear constraints in each round. Existing methods for SLBs provide strong regret guarantees,…

机器学习 · 计算机科学 2025-06-19 Aditya Gangrade , Venkatesh Saligrama

We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@$k$ and max@$k$. Given a posterior over arm values, ReMax chooses a sampling distribution that…

机器学习 · 计算机科学 2026-05-21 Bingkui Tong , Junpei Komiyama , Soichiro Nishimori , Paavo Parmas

This paper introduces and addresses a wide class of stochastic bandit problems where the function mapping the arm to the corresponding reward exhibits some known structural properties. Most existing structures (e.g. linear, Lipschitz,…

机器学习 · 统计学 2017-11-02 Richard Combes , Stefan Magureanu , Alexandre Proutiere

We consider the combinatorial bandits problem, where at each time step, the online learner selects a size-$k$ subset $s$ from the arms set $\mathcal{A}$, where $\left|\mathcal{A}\right| = n$, and observes a stochastic reward of each arm in…

机器学习 · 计算机科学 2021-03-05 Shuo Yang , Tongzheng Ren , Inderjit S. Dhillon , Sujay Sanghavi

We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two most common nonlinear contextual bandit settings: Generalized Linear Ensemble Sampling (GLM-ES)…

机器学习 · 计算机科学 2026-05-12 Jiazheng Sun , Weixin Wang , Pan Xu

Monte Carlo Tree Search (MCTS) has proven effective in solving decision-making problems in perfect information settings. However, its application to stochastic and imperfect information domains remains limited. This paper extends the…

机器学习 · 计算机科学 2025-02-12 Can Cömer , Jannis Blüml , Cedric Derstroff , Kristian Kersting

Stochastic rising rested bandit (SRRB) is a setting where the arms' expected rewards increase as they are pulled. It models scenarios in which the performances of the different options grow as an effect of an underlying learning process…

机器学习 · 统计学 2025-05-21 Marco Fiandri , Alberto Maria Metelli , Francesco Trovò

We study stochastic multi-armed bandits under simultaneous constraints on space and adaptivity: the learner interacts with the environment in $B$ batches and has only $W$ bits of persistent memory. Prior work shows that each constraint…

机器学习 · 计算机科学 2026-03-31 Ruiyuan Huang , Zicheng Lyu , Xiaoyi Zhu , Zengfeng Huang

This paper unifies the design and the analysis of risk-averse Thompson sampling algorithms for the multi-armed bandit problem for a class of risk functionals $\rho$ that are continuous and dominant. We prove generalised concentration bounds…

机器学习 · 计算机科学 2022-04-19 Joel Q. L. Chang , Vincent Y. F. Tan

Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS…

机器学习 · 计算机科学 2015-03-13 Niranjan Srinivas , Andreas Krause , Sham M. Kakade , Matthias Seeger

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…

机器学习 · 计算机科学 2018-06-08 Chen-Yu Wei , Haipeng Luo

We introduce a novel anytime Batched Thompson sampling policy for multi-armed bandits where the agent observes the rewards of her actions and adjusts her policy only at the end of a small number of batches. We show that this policy…

机器学习 · 计算机科学 2021-10-04 Cem Kalkanli , Ayfer Ozgur

This paper is in the field of stochastic Multi-Armed Bandits (MABs), i.e. those sequential selection techniques able to learn online using only the feedback given by the chosen option (a.k.a. $arm$). We study a particular case of the rested…

机器学习 · 统计学 2024-11-28 Marco Fiandri , Alberto Maria Metelli , Francesco Trov`o

Reinforcement learning is an attractive approach to learn good resource allocation and scheduling policies based on data when the system model is unknown. However, the cumulative regret of most RL algorithms scales as $\tilde O(\mathsf{S}…

机器学习 · 计算机科学 2023-04-28 Nima Akbarzadeh , Aditya Mahajan

Bayesian optimization is a framework for global search via maximum a posteriori updates rather than simulated annealing, and has gained prominence for decision-making under uncertainty. In this work, we cast Bayesian optimization as a…

机器学习 · 计算机科学 2022-03-24 Amrit Singh Bedi , Dheeraj Peddireddy , Vaneet Aggarwal , Brian M. Sadler , Alec Koppel

We study multi-armed bandit problems with graph feedback, in which the decision maker is allowed to observe the neighboring actions of the chosen action, in a setting where the graph may vary over time and is never fully revealed to the…

机器学习 · 统计学 2018-05-24 Fang Liu , Zizhan Zheng , Ness Shroff

Gaussian process (GP) bandits provide a powerful framework for performing blackbox optimization of unknown functions. The characteristics of the unknown function depend heavily on the assumed GP prior. Most work in the literature assume…

机器学习 · 计算机科学 2026-03-13 Jack Sandberg , Morteza Haghir Chehreghani

Wireless communication systems operate in complex time-varying environments. Therefore, selecting the optimal configuration parameters in these systems is a challenging problem. For wireless links, \emph{rate selection} is used to select…

机器学习 · 计算机科学 2020-04-21 Vidit Saxena , Joseph E. Gonzalez , Ion Stoica , Hugo Tullberg , Joakim Jaldén

The problem of multi-armed bandits (MAB) asks to make sequential decisions while balancing between exploitation and exploration, and have been successfully applied to a wide range of practical scenarios. Various algorithms have been…

机器学习 · 计算机科学 2022-02-24 Xiaojin Zhang , Shuai Li , Weiwen Liu , Shengyu Zhang

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…

机器学习 · 计算机科学 2019-10-15 Young Hun Jung , Marc Abeille , Ambuj Tewari