English
Related papers

Related papers: Doubly Robust Policy Evaluation and Learning

200 papers

Research on the multi-armed bandit problem has studied the trade-off of exploration and exploitation in depth. However, there are numerous applications where the cardinal absolute-valued feedback model (e.g. ratings from one to five) is not…

Machine Learning · Computer Science 2018-12-12 Lennard Hilgendorf

We study the fundamental limits of learning in contextual bandits, where a learner's rewards depend on their actions and a known context, which extends the canonical multi-armed bandit to the case where side-information is available. We are…

Machine Learning · Statistics 2023-06-13 Moise Blanchard , Steve Hanneke , Patrick Jaillet

Doubly robust learning offers a robust framework for causal inference from observational data by integrating propensity score and outcome modeling. Despite its theoretical appeal, practical adoption remains limited due to perceived…

Machine Learning · Statistics 2024-07-09 Hlynur Davíð Hlynsson

Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a simulation environment to…

Machine Learning · Computer Science 2021-11-23 Sai Kiran Narayanaswami , Nandan Sudarsanam , Balaraman Ravindran

Offline reinforcement learning, wherein one uses off-policy data logged by a fixed behavior policy to evaluate and learn new policies, is crucial in applications where experimentation is limited such as medicine. We study the estimation of…

Machine Learning · Computer Science 2020-06-09 Nathan Kallus , Masatoshi Uehara

We introduce the cram method as a general statistical framework for evaluating the final learned policy from a multi-armed contextual bandit algorithm, using the dataset generated by the same bandit algorithm. The proposed on-policy…

Machine Learning · Computer Science 2025-04-16 Zeyang Jia , Kosuke Imai , Michael Lingzhi Li

In many biomedical, science, and engineering problems, one must sequentially decide which action to take next so as to maximize rewards. One general class of algorithms for optimizing interactions with the world, while simultaneously…

Machine Learning · Statistics 2021-05-05 Iñigo Urteaga , Chris H. Wiggins

In today's technology environment, information is abundant, dynamic, and heterogeneous in nature. Automated filtering and prioritization of information is based on the distinction between whether the information adds substantial value…

Machine Learning · Computer Science 2022-02-01 Jade Freeman , Michael Rawson

Contextual bandits can solve a huge range of real-world problems. However, current popular algorithms to solve them either rely on linear models, or unreliable uncertainty estimation in non-linear models, which are required to deal with the…

Machine Learning · Computer Science 2023-02-01 Adam Elwood , Marco Leonardi , Ashraf Mohamed , Alessandro Rozza

Many applied decision-making problems have a dynamic component: The policymaker needs not only to choose whom to treat, but also when to start which treatment. For example, a medical doctor may choose between postponing treatment (watchful…

Methodology · Statistics 2020-05-01 Xinkun Nie , Emma Brunskill , Stefan Wager

Contextual bandit algorithms are ubiquitous tools for active sequential experimentation in healthcare and the tech industry. They involve online learning algorithms that adaptively learn policies over time to map observed contexts $X_t$ to…

Methodology · Statistics 2024-08-19 Ian Waudby-Smith , Lili Wu , Aaditya Ramdas , Nikos Karampatziakis , Paul Mineiro

We propose a new sequential decision-making setting, combining key aspects of two established online learning problems with bandit feedback. The optimal action to play at any given moment is contingent on an underlying changing state which…

Machine Learning · Computer Science 2023-11-07 Alexander Galozy , Slawomir Nowaczyk , Mattias Ohlsson

In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important…

Machine Learning · Computer Science 2016-04-05 Philip S. Thomas , Emma Brunskill

We consider off-policy selection and learning in contextual bandits, where the learner aims to select or train a reward-maximizing policy using data collected by a fixed behavior policy. Our contribution is two-fold. First, we propose a…

Machine Learning · Computer Science 2025-07-15 J. Jon Ryu , Jeongyeol Kwon , Benjamin Koppe , Kwang-Sung Jun

A contextual bandit problem is studied in a highly non-stationary environment, which is ubiquitous in various recommender systems due to the time-varying interests of users. Two models with disjoint and hybrid payoffs are considered to…

Machine Learning · Computer Science 2020-03-03 Xiao Xu , Fang Dong , Yanghua Li , Shaojian He , Xin Li

Equitably allocating limited resources in high-stakes domains-such as education, employment, and healthcare-requires balancing short-term utility with long-term impact, while accounting for delayed outcomes, hidden heterogeneity, and…

Artificial Intelligence · Computer Science 2025-11-17 Mohammadsina Almasi , Hadis Anahideh

In this work we revisit two classic high-dimensional online learning problems, namely linear regression and contextual bandits, from the perspective of adversarial robustness. Existing works in algorithmic robust statistics make strong…

Machine Learning · Computer Science 2021-06-14 Sitan Chen , Frederic Koehler , Ankur Moitra , Morris Yau

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Samin Yeasar Arnob , Doina Precup

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

The contextual bandit framework is widely used to solve sequential optimization problems where the reward of each decision depends on auxiliary context variables. In settings such as medicine, business, and engineering, the decision maker…

Machine Learning · Statistics 2025-03-17 Kevin Li , Eric Laber