English
Related papers

Related papers: Leave No One Undermined: Policy Targeting with Reg…

200 papers

We consider systems that require timely monitoring of sources over a communication network, where the cost of delayed information is unknown, time-varying and possibly adversarial. For the single source monitoring problem, we design…

Networking and Internet Architecture · Computer Science 2021-05-31 Vishrant Tripathi , Eytan Modiano

Off-policy learning is a framework for optimizing policies without deploying them, using data collected by another policy. In recommender systems, this is especially challenging due to the imbalance in logged data: some items are…

Machine Learning · Computer Science 2024-10-23 Matej Cief , Branislav Kveton , Michal Kompan

This paper proposes a novel method to estimate individualised treatment assignment rules. The method is designed to find rules that are stochastic, reflecting uncertainty in estimation of an assignment rule and about its welfare…

Econometrics · Economics 2023-02-22 Toru Kitagawa , Hugo Lopez , Jeff Rowley

Firms increasingly delegate decisions to learning algorithms in platform markets. Standard algorithms perform well when platform policies are stationary, but firms often face ambiguity about whether policies are stationary or adapt…

Theoretical Economics · Economics 2026-02-11 Kyohei Okumura

A crucial problem in reinforcement learning is learning the optimal policy. We study this in tabular infinite-horizon discounted Markov decision processes under the online setting. The existing algorithms either fail to achieve regret…

Machine Learning · Computer Science 2023-12-13 Xiang Ji , Gen Li

What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention…

Machine Learning · Computer Science 2024-10-31 Alexander Rutherford , Michael Beukman , Timon Willi , Bruno Lacerda , Nick Hawes , Jakob Foerster

Public policies and medical interventions often involve dynamic treatment assignments, in which individuals receive a sequence of interventions over multiple stages. We study the statistical learning of optimal dynamic treatment regimes…

Methodology · Statistics 2025-05-21 Shosei Sakaguchi

We define an online learning and optimization problem with discrete and irreversible decisions contributing toward a coverage target. In each period, a decision-maker selects facilities to open, receives information on the success of each…

Machine Learning · Computer Science 2026-03-06 Alexandre Jacquillat , Michael Lingzhi Li

The stochastic multi-armed bandit problem is a well-known model for studying the exploration-exploitation trade-off. It has significant possible applications in adaptive clinical trials, which allow for dynamic changes in the treatment…

Machine Learning · Computer Science 2019-06-11 Hossein Aboutalebi , Doina Precup , Tibor Schuster

Randomized controlled trials are often run in settings with many subpopulations that may have differential benefits from the treatment being evaluated. We consider the problem of sample selection, i.e., whom to enroll in a randomized trial,…

Methodology · Statistics 2024-06-26 Yuchen Hu , Henry Zhu , Emma Brunskill , Stefan Wager

We develop a novel method for personalized off-policy learning in scenarios with unobserved confounding. Thereby, we address a key limitation of standard policy learning: standard policy learning assumes unconfoundedness, meaning that no…

Machine Learning · Computer Science 2026-02-18 Konstantin Hess , Dennis Frauen , Valentyn Melnychuk , Stefan Feuerriegel

Minimizing volatility and adjustment costs is of central importance in many economic environments, yet it is often complicated by evolving feasibility constraints. We study a decision maker who repeatedly selects an action from a…

Theoretical Economics · Economics 2026-02-18 Simon Jantschgi , Heinrich H. Nax , Bary S. R. Pradelski , Marek Pycia

State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered…

Machine Learning · Computer Science 2019-11-01 Yonathan Efroni , Nadav Merlis , Mohammad Ghavamzadeh , Shie Mannor

The minmax regret problem for combinatorial optimization under uncertainty can be viewed as a zero-sum game played between an optimizing player and an adversary, where the optimizing player selects a solution and the adversary selects costs…

Discrete Mathematics · Computer Science 2014-09-23 Andrew Mastin , Patrick Jaillet , Sang Chin

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

This study introduces an agent-based model to study how regret, uncertainty, and social norms interact to shape vaccination behavior during epidemics. The model integrates three behavioral mechanisms, anticipated regret, evolving norms, and…

Physics and Society · Physics 2025-11-18 Christos Charalambous

Probabilistic classifiers are central for making informed decisions under uncertainty. Based on the maximum expected utility principle, optimal decision rules can be derived using the posterior class probabilities and misclassification…

Machine Learning · Computer Science 2025-03-25 Alexandre Perez-Lebel , Gael Varoquaux , Sanmi Koyejo , Matthieu Doutreligne , Marine Le Morvan

Incentive design constitutes a foundational paradigm for influencing the behavior of strategic agents, wherein a system planner (principal) publicly commits to an incentive mechanism designed to align individual objectives with collective…

Optimization and Control · Mathematics 2026-04-08 Georgios Vasileiou , Lantian Zhang , Silun Zhang

We study a framework where agents have to avoid aversive signals. The agents are given only partial information, in the form of features that are projections of task states. Additionally, the agents have to cope with non-determinism,…

Artificial Intelligence · Computer Science 2016-05-17 Tom J. Ameloot

Towards bridging classical optimal control and online learning, regret minimization has recently been proposed as a control design criterion. This competitive paradigm penalizes the loss relative to the optimal control actions chosen by a…

Systems and Control · Electrical Eng. & Systems 2023-06-27 Andrea Martin , Luca Furieri , Florian Dörfler , John Lygeros , Giancarlo Ferrari-Trecate