中文
相关论文

相关论文: Regularized OFU: an Efficient UCB Estimator forNon…

200 篇论文

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…

机器学习 · 计算机科学 2019-04-05 Haipeng Luo , Chen-Yu Wei , Alekh Agarwal , John Langford

We present an algorithm based on the \emph{Optimism in the Face of Uncertainty} (OFU) principle which is able to learn Reinforcement Learning (RL) modeled by Markov decision process (MDP) with finite state-action space efficiently. By…

机器学习 · 计算机科学 2020-01-01 Zihan Zhang , Xiangyang Ji

Recent works on neural contextual bandits have achieved compelling performances due to their ability to leverage the strong representation power of neural networks (NNs) for reward prediction. Many applications of contextual bandits involve…

机器学习 · 计算机科学 2023-03-02 Zhongxiang Dai , Yao Shu , Arun Verma , Flint Xiaofeng Fan , Bryan Kian Hsiang Low , Patrick Jaillet

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…

机器学习 · 计算机科学 2011-11-10 Wenhan Dai , Yi Gai , Bhaskar Krishnamachari

A major research direction in contextual bandits is to develop algorithms that are computationally efficient, yet support flexible, general-purpose function approximation. Algorithms based on modeling rewards have shown strong empirical…

机器学习 · 计算机科学 2021-07-14 Dylan J. Foster , Claudio Gentile , Mehryar Mohri , Julian Zimmert

Upper Confidence Bound (UCB) is arguably the most commonly used method for linear multi-arm bandit problems. While conceptually and computationally simple, this method highly relies on the confidence bounds, failing to strike the optimal…

机器学习 · 计算机科学 2020-06-05 Kaige Yang , Laura Toni

The upper confidence bound (UCB) policy is recognized as an order-optimal solution for the classical total-reward bandit problem. While similar UCB-based approaches have been applied to the max bandit problem, which aims to maximize the…

机器学习 · 统计学 2024-11-04 Nobuaki Kikkawa , Hiroshi Ohno

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…

机器学习 · 计算机科学 2021-06-14 Sanath Kumar Krishnamurthy , Vitor Hadad , Susan Athey

This paper considers a stochastic Multi-Armed Bandit (MAB) problem with dual objectives: (i) quick identification and commitment to the optimal arm, and (ii) reward maximization throughout a sequence of $T$ consecutive rounds. Though each…

机器学习 · 计算机科学 2024-05-31 Qining Zhang , Lei Ying

Safety is a desirable property that can immensely increase the applicability of learning algorithms in real-world decision-making problems. It is much easier for a company to deploy an algorithm that is safe, i.e., guaranteed to perform at…

机器学习 · 统计学 2017-03-07 Abbas Kazerouni , Mohammad Ghavamzadeh , Yasin Abbasi-Yadkori , Benjamin Van Roy

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…

机器学习 · 统计学 2025-10-17 Joongkyu Lee , Min-hwan Oh

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 study contextual bandits with nonlinear and path-dependent rewards through a novel signature-transform-based approach. Leveraging the universal nonlinearity property of signatures, we approximate continuous path-dependent reward…

机器学习 · 计算机科学 2026-05-12 Xin Guo , Grace He , Xinyu Li

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…

机器学习 · 计算机科学 2026-03-12 Heyang Zhao , Chenlu Ye , Wei Xiong , Quanquan Gu , Tong Zhang

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,…

机器学习 · 统计学 2024-02-13 Chenlu Ye , Wei Xiong , Quanquan Gu , Tong Zhang

We consider the neural contextual bandit problem. In contrast to the existing work which primarily focuses on ReLU neural nets, we consider a general set of smooth activation functions. Under this more general setting, (i) we derive…

机器学习 · 统计学 2022-06-02 Sudeep Salgia , Sattar Vakili , Qing Zhao

Most existing studies on linear bandits focus on the one-dimensional characterization of the overall system. While being representative, this formulation may fail to model applications with high-dimensional but favorable structures, such as…

机器学习 · 统计学 2023-05-09 Chengshuai Shi , Cong Shen , Nicholas D. Sidiropoulos

We study the Logistic Contextual Slate Bandit problem, where, at each round, an agent selects a slate of $N$ items from an exponentially large set (of size $2^{\Omega(N)}$) of candidate slates provided by the environment. A single binary…

机器学习 · 计算机科学 2026-05-13 Tanmay Goyal , Gaurav Sinha

We consider the general (stochastic) contextual bandit problem under the realizability assumption, i.e., the expected reward, as a function of contexts and actions, belongs to a general function class $\mathcal{F}$. We design a fast and…

机器学习 · 计算机科学 2021-07-13 David Simchi-Levi , Yunzong Xu

We study budget-constrained contextual bandits with adversarial contexts, where each action yields a random reward and incurs a random cost. We adopt the standard realizability assumption: conditioned on the observed context, rewards and…

机器学习 · 计算机科学 2026-05-08 Dhruv Sarkar , Abhishek Sinha