中文
相关论文

相关论文: Improved Regret Analysis in Gaussian Process Bandi…

200 篇论文

In this paper we propose a general methodology to derive regret bounds for randomized multi-armed bandit algorithms. It consists in checking a set of sufficient conditions on the sampling probability of each arm and on the family of…

机器学习 · 计算机科学 2024-11-14 Dorian Baudry , Kazuya Suzuki , Junya Honda

We study the problem of nonstochastic bandits with expert advice, extending the setting from finitely many experts to any countably infinite set: A learner aims to maximize the total reward by taking actions sequentially based on bandit…

机器学习 · 计算机科学 2021-03-29 X. Flora Meng , Tuhin Sarkar , Munther A. Dahleh

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…

机器学习 · 计算机科学 2022-06-14 Aadirupa Saha , Shubham Gupta

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…

机器学习 · 计算机科学 2023-10-19 Haolin Liu , Chen-Yu Wei , Julian Zimmert

We consider a kernelized bandit problem with a compact arm set ${X} \subset \mathbb{R}^d $ and a fixed but unknown reward function $f^*$ with a finite norm in some Reproducing Kernel Hilbert Space (RKHS). We propose a class of…

机器学习 · 计算机科学 2025-06-13 Bingshan Hu , Zheng He , Danica J. Sutherland

We study a distributed stochastic multi-armed bandit where a client supplies the learner with communication-constrained feedback based on the rewards for the corresponding arm pulls. In our setup, the client must encode the rewards such…

机器学习 · 计算机科学 2023-06-07 Prathamesh Mayekar , Jonathan Scarlett , Vincent Y. F. Tan

We study the constrained variant of the \emph{multi-armed bandit} (MAB) problem, in which the learner aims not only at minimizing the total loss incurred during the learning dynamic, but also at controlling the violation of multiple…

This work addresses the problem of regret minimization in non-stochastic multi-armed bandit problems, focusing on performance guarantees that hold with high probability. Such results are rather scarce in the literature since proving them…

机器学习 · 计算机科学 2015-11-04 Gergely Neu

I introduce and analyse an anytime version of the Optimally Confident UCB (OCUCB) algorithm designed for minimising the cumulative regret in finite-armed stochastic bandits with subgaussian noise. The new algorithm is simple, intuitive (in…

机器学习 · 计算机科学 2016-05-09 Tor Lattimore

We study the Stochastic Shortest Path (SSP) problem with a linear mixture transition kernel, where an agent repeatedly interacts with a stochastic environment and seeks to reach certain goal state while minimizing the cumulative cost.…

机器学习 · 计算机科学 2024-02-15 Qiwei Di , Jiafan He , Dongruo Zhou , Quanquan Gu

We consider the problem of Bayesian optimization (BO) in one dimension, under a Gaussian process prior and Gaussian sampling noise. We provide a theoretical analysis showing that, under fairly mild technical assumptions on the kernel, the…

机器学习 · 统计学 2025-05-08 Jonathan Scarlett

We study the linear stochastic bandit problem, relaxing the standard i.i.d. assumption on the observation noise. As an alternative to this restrictive assumption, we allow the noise terms across rounds to be sub-Gaussian but interdependent,…

机器学习 · 统计学 2025-05-28 Baptiste Abélès , Eugenio Clerico , Hamish Flynn , Gergely Neu

In this paper, we study the problem of fair sequential decision making with biased linear bandit feedback. At each round, a player selects an action described by a covariate and by a sensitive attribute. The perceived reward is a linear…

统计理论 · 数学 2022-06-06 Solenne Gaucher , Alexandra Carpentier , Christophe Giraud

Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation. When it comes to a finite-horizon episodic Markov decision process with $S$ states, $A$ actions and…

机器学习 · 计算机科学 2022-10-18 Gen Li , Laixi Shi , Yuxin Chen , Yuejie Chi

Bandit algorithms have been predominantly analyzed in the convex setting with function-value based stationary regret as the performance measure. In this paper, motivated by online reinforcement learning problems, we propose and analyze…

机器学习 · 统计学 2019-09-12 Abhishek Roy , Krishnakumar Balasubramanian , Saeed Ghadimi , Prasant Mohapatra

We study a stochastic bandit problem with a general unknown reward function and a general unknown constraint function. Both functions can be non-linear (even non-convex) and are assumed to lie in a reproducing kernel Hilbert space (RKHS)…

机器学习 · 计算机科学 2022-03-30 Xingyu Zhou , Bo Ji

We study contextual bandits in the presence of a stage-wise constraint when the constraint must be satisfied both with high probability and in expectation. We start with the linear case where both the reward function and the stage-wise…

机器学习 · 计算机科学 2025-08-22 Aldo Pacchiano , Mohammad Ghavamzadeh , Peter Bartlett

We investigate bandit convex optimization (BCO) with delayed feedback, where only the loss value of the action is revealed under an arbitrary delay. Let $n,T,\bar{d}$ denote the dimensionality, time horizon, and average delay, respectively.…

机器学习 · 计算机科学 2024-06-25 Yuanyu Wan , Chang Yao , Mingli Song , Lijun Zhang

We present regret minimization algorithms for the contextual multi-armed bandit (CMAB) problem over $K$ actions in the presence of delayed feedback, a scenario where loss observations arrive with delays chosen by an adversary. As a…

机器学习 · 计算机科学 2025-10-13 Orin Levy , Liad Erez , Alon Cohen , Yishay Mansour

Mean rewards of actions are often correlated. The form of these correlations may be complex and unknown a priori, such as the preferences of a user for recommended products and their categories. To maximize statistical efficiency, it is…

机器学习 · 计算机科学 2022-02-04 Joey Hong , Branislav Kveton , Sumeet Katariya , Manzil Zaheer , Mohammad Ghavamzadeh
‹ 上一页 1 8 9 10 下一页 ›