中文
相关论文

相关论文: Optimal and Adaptive Off-policy Evaluation in Cont…

200 篇论文

Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback over the selected arms for the past contexts. However,…

机器学习 · 计算机科学 2025-04-17 Arun Verma , Zhongxiang Dai , Xiaoqiang Lin , Patrick Jaillet , Bryan Kian Hsiang Low

We study nonparametric contextual bandits where Lipschitz mean reward functions may change over time. We first establish the minimax dynamic regret rate in this less understood setting in terms of number of changes $L$ and total-variation…

机器学习 · 统计学 2023-11-21 Joe Suk , Samory Kpotufe

We consider contextual bandits with knapsacks, with an underlying structure between rewards generated and cost vectors suffered. We do so motivated by sales with commercial discounts. At each round, given the stochastic i.i.d.\ context…

机器学习 · 计算机科学 2022-10-03 Zhen Li , Gilles Stoltz

We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies. In…

机器学习 · 计算机科学 2019-12-16 Aurélien F. Bibaut , Ivana Malenica , Nikos Vlassis , Mark J. van der Laan

We study bandit learning in matching markets, where players and arms constitute the two market sides, and the players' utilities are linear in the arm contexts. In each round, new arms arrive with observable contexts. Then, the algorithm…

机器学习 · 计算机科学 2026-05-28 Shiyun Lin , Simon Mauras , Vianney Perchet , Nadav Merlis

We study the policy evaluation problem in an online multi-reward multi-policy discounted setting, where multiple reward functions must be evaluated simultaneously for different policies. We adopt an $(\epsilon,\delta)$-PAC perspective to…

机器学习 · 计算机科学 2025-08-19 Alessio Russo , Aldo Pacchiano

We investigate the adversarial bandit problem with multiple plays under semi-bandit feedback. We introduce a highly efficient algorithm that asymptotically achieves the performance of the best switching $m$-arm strategy with minimax optimal…

机器学习 · 计算机科学 2019-12-02 N. Mert Vural , Hakan Gokcesu , Kaan Gokcesu , Suleyman S. Kozat

A standard assumption in contextual multi-arm bandit is that the true context is perfectly known before arm selection. Nonetheless, in many practical applications (e.g., cloud resource management), prior to arm selection, the context…

机器学习 · 计算机科学 2021-04-06 Jianyi Yang , Shaolei Ren

Off-policy evaluation provides an essential tool for evaluating the effects of different policies or treatments using only observed data. When applied to high-stakes scenarios such as medical diagnosis or financial decision-making, it is…

机器学习 · 计算机科学 2020-10-30 Ziyang Tang , Yihao Feng , Na Zhang , Jian Peng , Qiang Liu

Many works have developed no-regret algorithms for contextual bandits with function approximation, where the mean reward function over context-action pairs belongs to a function class. Although there are many approaches to this problem, one…

机器学习 · 计算机科学 2025-03-18 Aldo Pacchiano

Existing data-dependent and best-of-both-worlds regret bounds for multi-armed bandits problems have limited adaptivity as they are either data-dependent but not best-of-both-worlds (BOBW), BOBW but not data-dependent or have sub-optimal…

机器学习 · 计算机科学 2025-02-13 Quan Nguyen , Shinji Ito , Junpei Komiyama , Nishant A. Mehta

We consider the problem where M agents collaboratively interact with an instance of a stochastic K-armed contextual bandit, where K>>M. The goal of the agents is to simultaneously minimize the cumulative regret over all the agents over a…

机器学习 · 计算机科学 2022-11-16 Jiabin Lin , Shana Moothedath

Contextual multi-armed bandit (MAB) achieves cutting-edge performance on a variety of problems. When it comes to real-world scenarios such as recommendation system and online advertising, however, it is essential to consider the resource…

机器学习 · 计算机科学 2020-04-07 Mengyue Yang , Qingyang Li , Zhiwei Qin , Jieping Ye

Contextual bandits are widely-used in the study of learning-based control policies for finite action spaces. While the problem is well-studied for bandits with perfectly observed context vectors, little is known about the case of…

机器学习 · 统计学 2022-02-03 Hongju Park , Mohamad Kazem Shirani Faradonbeh

We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as contextual bandits, encompasses a wide variety of…

机器学习 · 计算机科学 2011-05-09 Miroslav Dudik , John Langford , Lihong Li

Contextual bandits have become an increasingly popular solution for personalized recommender systems. Despite their growing use, the interpretability of these systems remains a significant challenge, particularly for the often non-expert…

机器学习 · 计算机科学 2024-09-24 Andrew Maher , Matia Gobbo , Lancelot Lachartre , Subash Prabanantham , Rowan Swiers , Puli Liyanagama

We study the adversarial bandit problem against arbitrary strategies, where the difficulty is captured by an unknown parameter $S$, which is the number of switches in the best arm in hindsight. To handle this problem, we adopt the…

机器学习 · 计算机科学 2025-11-26 Jung-hun Kim , Se-Young Yun

Contextual multi-armed bandits are a popular choice to model sequential decision-making. E.g., in a healthcare application we may perform various tests to asses a patient condition (exploration) and then decide on the best treatment to give…

机器学习 · 计算机科学 2025-04-08 Mirco Mutti , Jeongyeol Kwon , Shie Mannor , Aviv Tamar

Off-policy evaluation is a key component of reinforcement learning which evaluates a target policy with offline data collected from behavior policies. It is a crucial step towards safe reinforcement learning and has been used in…

机器学习 · 计算机科学 2020-12-01 Jinlin Lai , Lixin Zou , Jiaxing Song

Motivated by applications in online bidding and sleeping bandits, we examine the problem of contextual bandits with cross learning, where the learner observes the loss associated with the action across all possible contexts, not just the…

机器学习 · 计算机科学 2025-01-27 Ruiyuan Huang , Zengfeng Huang