English
Related papers

Related papers: Sample-efficient Nonstationary Policy Evaluation f…

200 papers

We study the problem of online learning in adversarial bandit problems under a partial observability model called off-policy feedback. In this sequential decision making problem, the learner cannot directly observe its rewards, but instead…

Machine Learning · Computer Science 2022-07-20 Germano Gabbianelli , Matteo Papini , Gergely Neu

Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances in OPL primarily optimize OPE estimators with improved statistical properties, assuming that…

Machine Learning · Statistics 2025-09-04 Imad Aouali , Otmane Sakhi

Contextual bandits have the same exploration-exploitation trade-off as standard multi-armed bandits. On adding positive externalities that decay with time, this problem becomes much more difficult as wrong decisions at the start are hard to…

Machine Learning · Computer Science 2019-11-15 Harsh Deshpande , Vishal Jain , Sharayu Moharir

Learning effective contextual-bandit policies from past actions of a deployed system is highly desirable in many settings (e.g. voice assistants, recommendation, search), since it enables the reuse of large amounts of log data.…

Machine Learning · Computer Science 2020-06-18 Noveen Sachdeva , Yi Su , Thorsten Joachims

We propose a robust regression approach to off-policy evaluation (OPE) for contextual bandits. We frame OPE as a covariate-shift problem and leverage modern robust regression tools. Ours is a general approach that can be used to augment any…

Machine Learning · Computer Science 2019-11-19 Anqi Liu , Hao Liu , Anima Anandkumar , Yisong Yue

In production systems, contextual bandit approaches often rely on direct reward models that take both action and context as input. However, these models can suffer from confounding, making it difficult to isolate the effect of the action…

Machine Learning · Computer Science 2025-09-16 Alexandre Gilotte , Otmane Sakhi , Imad Aouali , Benjamin Heymann

Maximizing long-term rewards is the primary goal in sequential decision-making problems. The majority of existing methods assume that side information is freely available, enabling the learning agent to observe all features' states before…

Machine Learning · Computer Science 2023-07-19 Saeed Ghoorchian , Evgenii Kortukov , Setareh Maghsudi

We explore off-policy evaluation and learning (OPE/L) in contextual combinatorial bandits (CCB), where a policy selects a subset in the action space. For example, it might choose a set of furniture pieces (a bed and a drawer) from available…

Machine Learning · Statistics 2024-08-22 Tatsuhiro Shimizu , Koichi Tanaka , Ren Kishimoto , Haruka Kiyohara , Masahiro Nomura , Yuta Saito

In the stochastic linear contextual bandit setting there exist several minimax procedures for exploration with policies that are reactive to the data being acquired. In practice, there can be a significant engineering overhead to deploy…

Machine Learning · Computer Science 2021-07-26 Andrea Zanette , Kefan Dong , Jonathan Lee , Emma Brunskill

An agent in a nonstationary contextual bandit problem should balance between exploration and the exploitation of (periodic or structured) patterns present in its previous experiences. Handcrafting an appropriate historical context is an…

Machine Learning · Computer Science 2023-11-06 Aditya Ramesh , Paulo Rauber , Michelangelo Conserva , Jürgen Schmidhuber

Contextual bandit algorithms have become popular for online recommendation systems such as Digg, Yahoo! Buzz, and news recommendation in general. \emph{Offline} evaluation of the effectiveness of new algorithms in these applications is…

Machine Learning · Computer Science 2015-03-13 Lihong Li , Wei Chu , John Langford , Xuanhui Wang

In some applications of reinforcement learning, a dataset of pre-collected experience is already available but it is also possible to acquire some additional online data to help improve the quality of the policy. However, it may be…

Machine Learning · Computer Science 2023-07-11 Ruiqi Zhang , Andrea Zanette

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates the policy based on past observations, the samples are not…

Machine Learning · Computer Science 2020-10-27 Masahiro Kato , Yusuke Kaneko

Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement. However, such algorithms usually…

Machine Learning · Computer Science 2018-05-25 Qingyun Wu , Naveen Iyer , Hongning Wang

In this paper, we study representation learning for multi-task decision-making in non-stationary environments. We consider the framework of sequential linear bandits, where the agent performs a series of tasks drawn from distinct sets…

Machine Learning · Computer Science 2022-04-19 Yuzhen Qin , Tommaso Menara , Samet Oymak , ShiNung Ching , Fabio Pasqualetti

Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution $\mathcal{P}$. In this work, we learn such policies for an unknown distribution $\mathcal{P}$ using samples from…

Machine Learning · Computer Science 2020-06-11 Craig Boutilier , Chih-Wei Hsu , Branislav Kveton , Martin Mladenov , Csaba Szepesvari , Manzil Zaheer

Real-world applications of reinforcement learning for recommendation and experimentation faces a practical challenge: the relative reward of different bandit arms can evolve over the lifetime of the learning agent. To deal with these…

Machine Learning · Computer Science 2022-06-29 Srivas Chennu , Andrew Maher , Jamie Martin , Subash Prabanantham

Accurately evaluating new policies (e.g. ad-placement models, ranking functions, recommendation functions) is one of the key prerequisites for improving interactive systems. While the conventional approach to evaluation relies on online A/B…

Machine Learning · Computer Science 2017-06-27 Aman Agarwal , Soumya Basu , Tobias Schnabel , Thorsten Joachims

Offline policy optimization could have a large impact on many real-world decision-making problems, as online learning may be infeasible in many applications. Importance sampling and its variants are a commonly used type of estimator in…

Machine Learning · Computer Science 2022-07-05 Yao Liu , Yannis Flet-Berliac , Emma Brunskill

We study the efficient off-policy evaluation of natural stochastic policies, which are defined in terms of deviations from the behavior policy. This is a departure from the literature on off-policy evaluation where most work consider the…

Machine Learning · Computer Science 2020-11-05 Nathan Kallus , Masatoshi Uehara