English
Related papers

Related papers: Off-Policy Risk Assessment in Contextual Bandits

200 papers

We study policy evaluation of offline contextual bandits subject to unobserved confounders. Sensitivity analysis methods are commonly used to estimate the policy value under the worst-case confounding over a given uncertainty set. However,…

Machine Learning · Statistics 2026-01-13 Kei Ishikawa , Niao He , Takafumi Kanamori

When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challenges. Unlike classical supervised learning and online…

Machine Learning · Computer Science 2018-08-02 Yuan Xie , Boyi Liu , Qiang Liu , Zhaoran Wang , Yuan Zhou , Jian Peng

Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…

Machine Learning · Statistics 2024-02-20 Davide Mambelli , Stephan Bongers , Onno Zoeter , Matthijs T. J. Spaan , Frans A. Oliehoek

We study offline reinforcement learning in average-reward MDPs, which presents increased challenges from the perspectives of distribution shift and non-uniform coverage, and has been relatively underexamined from a theoretical perspective.…

Machine Learning · Computer Science 2026-04-23 Matthew Zurek , Guy Zamir , Yudong Chen

Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult…

Machine Learning · Computer Science 2018-12-18 Maria Dimakopoulou , Zhengyuan Zhou , Susan Athey , Guido Imbens

Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, we investigate a smooth regularization for IPS, for which we…

Machine Learning · Computer Science 2023-06-06 Imad Aouali , Victor-Emmanuel Brunel , David Rohde , Anna Korba

Off-policy evaluation (OPE) is a method for estimating the return of a target policy using some pre-collected observational data generated by a potentially different behavior policy. In some cases, there may be unmeasured variables that can…

Machine Learning · Statistics 2023-02-03 Yang Xu , Jin Zhu , Chengchun Shi , Shikai Luo , Rui Song

Training Reinforcement Learning (RL) agents in high-stakes applications might be too prohibitive due to the risk associated to exploration. Thus, the agent can only use data previously collected by safe policies. While previous work…

Machine Learning · Computer Science 2021-02-11 Núria Armengol Urpí , Sebastian Curi , Andreas Krause

We consider the problem of contextual bandits where actions are subsets of a ground set and mean rewards are modeled by an unknown monotone submodular function that belongs to a class $\mathcal{F}$. We allow time-varying matroid constraints…

Machine Learning · Computer Science 2021-12-07 Dean P. Foster , Alexander Rakhlin

This paper investigates the problem of online prediction learning, where learning proceeds continuously as the agent interacts with an environment. The predictions made by the agent are contingent on a particular way of behaving,…

Machine Learning · Computer Science 2018-11-08 Sina Ghiassian , Andrew Patterson , Martha White , Richard S. Sutton , Adam White

We introduce an off-policy evaluation procedure for highlighting episodes where applying a reinforcement learned (RL) policy is likely to have produced a substantially different outcome than the observed policy. In particular, we introduce…

Machine Learning · Computer Science 2021-03-04 Michael Oberst , David Sontag

Contextual bandits with average-case statistical guarantees are inadequate in risk-averse situations because they might trade off degraded worst-case behaviour for better average performance. Designing a risk-averse contextual bandit is…

Machine Learning · Statistics 2023-07-11 Mónika Farsang , Paul Mineiro , Wangda Zhang

We present the first high-probability optimal regret bound for a policy optimization technique applied to the problem of stochastic contextual multi-armed bandit (CMAB) with general offline function approximation. Our algorithm is both…

Machine Learning · Computer Science 2026-02-17 Orin Levy , Yishay Mansour

Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human…

Machine Learning · Computer Science 2023-06-01 Philip J. Ball , Laura Smith , Ilya Kostrikov , Sergey Levine

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…

Machine Learning · Computer Science 2020-12-01 Jinlin Lai , Lixin Zou , Jiaxing Song

We introduce a distributionally robust approach that enhances the reliability of offline policy evaluation in contextual bandits under general covariate shifts. Our method aims to deliver robust policy evaluation results in the presence of…

Machine Learning · Computer Science 2024-08-12 Yihong Guo , Hao Liu , Yisong Yue , Anqi Liu

This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inhomogeneities", we…

Methodology · Statistics 2024-08-20 Zeyu Bian , Chengchun Shi , Zhengling Qi , Lan Wang

We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value…

Machine Learning · Computer Science 2020-02-19 Omer Gottesman , Yao Liu , Scott Sussex , Emma Brunskill , Finale Doshi-Velez

We study a novel setting in offline reinforcement learning (RL) where a number of distributed machines jointly cooperate to solve the problem but only one single round of communication is allowed and there is a budget constraint on the…

Machine Learning · Statistics 2022-02-11 Juliusz Krysztof Ziomek , Jun Wang , Yaodong Yang

In decision-making problems such as the multi-armed bandit, an agent learns sequentially by optimizing a certain feedback. While the mean reward criterion has been extensively studied, other measures that reflect an aversion to adverse…

Machine Learning · Statistics 2023-03-28 Patrick Saux , Odalric-Ambrym Maillard