English
Related papers

Related papers: Regret Analysis of a Markov Policy Gradient Algori…

200 papers

In restless bandits, a central agent is tasked with optimally distributing limited resources across several bandits (arms), with each arm being a Markov decision process. In this work, we generalize the traditional restless bandits problem…

Machine Learning · Computer Science 2026-02-20 Nima Akbarzadeh , Yossiri Adulyasak , Erick Delage

We study the recovering bandits problem, a variant of the stochastic multi-armed bandit problem where the expected reward of each arm varies according to some unknown function of the time since the arm was last played. While being a natural…

Machine Learning · Statistics 2019-11-01 Ciara Pike-Burke , Steffen Grünewälder

Traditionally, when recommender systems are formalized as multi-armed bandits, the policy of the recommender system influences the rewards accrued, but not the length of interaction. However, in real-world systems, dissatisfied users may…

Machine Learning · Computer Science 2024-02-19 Omer Ben-Porat , Lee Cohen , Liu Leqi , Zachary C. Lipton , Yishay Mansour

We consider a stochastic multi-armed bandit problem with i.i.d. rewards where the expected reward function is multimodal with at most m modes. We propose the first known computationally tractable algorithm for computing the solution to the…

Machine Learning · Statistics 2025-10-31 William Réveillard , Richard Combes

A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation…

Machine Learning · Computer Science 2016-08-18 K J Prabuchandran , Tejas Bodas , Theja Tulabandhula

Experimentation with interference poses a significant challenge in contemporary online platforms. Prior research on experimentation with interference has concentrated on the final output of a policy. The cumulative performance, while…

Machine Learning · Computer Science 2024-07-17 Su Jia , Peter Frazier , Nathan Kallus

We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards. In this setup, the learner's goal is to identify atomic interventions that lead to high rewards by intervening on…

Machine Learning · Computer Science 2021-11-02 Rahul Madhavan , Aurghya Maiti , Gaurav Sinha , Siddharth Barman

This paper investigates stochastic multi-armed bandit algorithms that are robust to adversarial attacks, where an attacker can first observe the learner's action and {then} alter their reward observation. We study two cases of this model,…

Machine Learning · Computer Science 2024-08-19 Xuchuang Wang , Jinhang Zuo , Xutong Liu , John C. S. Lui , Mohammad Hajiesmaili

We consider the classical multi-armed bandit problem, but with strategic arms. In this context, each arm is characterized by a bounded support reward distribution and strategically aims to maximize its own utility by potentially retaining a…

Machine Learning · Computer Science 2025-01-28 Ahmed Ben Yahmed , Clément Calauzènes , Vianney Perchet

In many fields such as digital marketing, healthcare, finance, and robotics, it is common to have a well-tested and reliable baseline policy running in production (e.g., a recommender system). Nonetheless, the baseline policy is often…

Machine Learning · Computer Science 2020-02-11 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta

The multi-armed bandit (MAB) problem is a classical learning task that exemplifies the exploration-exploitation tradeoff. However, standard formulations do not take into account {\em risk}. In online decision making systems, risk is a…

Machine Learning · Computer Science 2020-08-04 Qiuyu Zhu , Vincent Y. F. Tan

Given a multi-armed bandit problem it may be desirable to achieve a smaller-than-usual worst-case regret for some special actions. I show that the price for such unbalanced worst-case regret guarantees is rather high. Specifically, if an…

Machine Learning · Computer Science 2015-11-03 Tor Lattimore

We study contextual bandits in the presence of a stage-wise constraint when the constraint must be satisfied both with high probability and in expectation. We start with the linear case where both the reward function and the stage-wise…

Machine Learning · Computer Science 2025-08-22 Aldo Pacchiano , Mohammad Ghavamzadeh , Peter Bartlett

Mode estimation is a classical problem in statistics with a wide range of applications in machine learning. Despite this, there is little understanding in its robustness properties under possibly adversarial data contamination. In this…

Machine Learning · Computer Science 2020-03-09 Aldo Pacchiano , Heinrich Jiang , Michael I. Jordan

We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@$k$ and max@$k$. Given a posterior over arm values, ReMax chooses a sampling distribution that…

Machine Learning · Computer Science 2026-05-21 Bingkui Tong , Junpei Komiyama , Soichiro Nishimori , Paavo Parmas

We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best…

Machine Learning · Computer Science 2021-03-02 Raman Arora , Teodor V. Marinov , Mehryar Mohri

We consider a stochastic bandit problem with a possibly infinite number of arms. We write $p^*$ for the proportion of optimal arms and $\Delta$ for the minimal mean-gap between optimal and sub-optimal arms. We characterize the optimal…

Machine Learning · Computer Science 2021-11-08 Rianne de Heide , James Cheshire , Pierre Ménard , Alexandra Carpentier

We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require carefully constructing optimistic and biased loss…

Machine Learning · Computer Science 2020-11-02 Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei , Mengxiao Zhang

In the latent bandit problem, the learner has access to reward distributions and -- for the non-stationary variant -- transition models of the environment. The reward distributions are conditioned on the arm and unknown latent states. The…

Machine Learning · Computer Science 2022-07-11 Alexander Galozy , Slawomir Nowaczyk

There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are…

Machine Learning · Statistics 2020-02-27 Aniket Anand Deshmukh , Srinagesh Sharma , James W. Cutler , Mark Moldwin , Clayton Scott