English
Related papers

Related papers: TSEB: More Efficient Thompson Sampling for Policy …

200 papers

Using bandit algorithms to conduct adaptive randomised experiments can minimise regret, but it poses major challenges for statistical inference (e.g., biased estimators, inflated type-I error and reduced power). Recent attempts to address…

Machine Learning · Statistics 2021-11-02 Nina Deliu , Joseph J. Williams , Sofia S. Villar

This paper investigates the challenges of optimal online policy learning under missing data. State-of-the-art algorithms implicitly assume that rewards are always observable. I show that when rewards are missing at random, the Upper…

Econometrics · Economics 2025-07-29 Filippo Palomba

Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world operates. One general class of algorithms for such learning…

Machine Learning · Statistics 2018-08-10 Iñigo Urteaga , Chris H. Wiggins

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Machine Learning · Computer Science 2021-01-07 Branislav Kveton , Martin Mladenov , Chih-Wei Hsu , Manzil Zaheer , Csaba Szepesvari , Craig Boutilier

Thompson Sampling (TS) is an efficient method for decision-making under uncertainty, where an action is sampled from a carefully prescribed distribution which is updated based on the observed data. In this work, we study the problem of…

Machine Learning · Computer Science 2022-06-20 Taylan Kargin , Sahin Lale , Kamyar Azizzadenesheli , Anima Anandkumar , Babak Hassibi

We consider the trade-off problem between exploration and exploitation under finite discounted Markov Decision Process, where the state transition matrix of the underlying environment stays unknown. We propose a double Thompson sampling…

Machine Learning · Computer Science 2022-03-01 Shuqing Shi , Xiaobin Wang , Zhiyou Yang , Fan Zhang , Hong Qu

We design and implement an adaptive experiment (a ``contextual bandit'') to learn a targeted treatment assignment policy, where the goal is to use a participant's survey responses to determine which charity to expose them to in a donation…

We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling. By making a connection between information-theoretic quantities and confidence bounds, we obtain results that relate…

Machine Learning · Statistics 2019-11-25 Xiuyuan Lu , Benjamin Van Roy

Thompson sampling has proven effective across a wide range of stationary bandit environments. However, as we demonstrate in this paper, it can perform poorly when applied to non-stationary environments. We attribute such failures to the…

Machine Learning · Computer Science 2025-05-06 Yueyang Liu , Xu Kuang , Benjamin Van Roy

Preference feedback, in the form of pairwise comparisons rather than scalar scores, has seen increasing use in applications such as human-, laboratory-, and expert-in-the-loop design, as well as scientific discovery. We propose a Thompson…

Machine Learning · Statistics 2026-04-29 Joseph Lazzaro , Davide Buffelli , Da-shan Shiu , Sattar Vakili

We address the problem of regret minimization in logistic contextual bandits, where a learner decides among sequential actions or arms given their respective contexts to maximize binary rewards. Using a fast inference procedure with…

Machine Learning · Statistics 2018-05-22 Bianca Dumitrascu , Karen Feng , Barbara E Engelhardt

Thompson Sampling (TS) from Gaussian Process (GP) models is a powerful tool for the optimization of black-box functions. Although TS enjoys strong theoretical guarantees and convincing empirical performance, it incurs a large computational…

Machine Learning · Statistics 2021-11-08 Sattar Vakili , Henry Moss , Artem Artemev , Vincent Dutordoir , Victor Picheny

We investigate the extent to which offline demonstration data can improve online learning. It is natural to expect some improvement, but the question is how, and by how much? We show that the degree of improvement must depend on the quality…

Machine Learning · Computer Science 2023-05-18 Botao Hao , Rahul Jain , Tor Lattimore , Benjamin Van Roy , Zheng Wen

The aim of this paper is to provide several novel upper bounds on the excess risk with a primal focus on classification problems. We suggest two approaches and the obtained bounds are represented via the distribution dependent local…

Statistics Theory · Mathematics 2018-03-13 Nikita Zhivotovskiy

Addressing uncertainty is critical for autonomous systems to robustly adapt to the real world. We formulate the problem of model uncertainty as a continuous Bayes-Adaptive Markov Decision Process (BAMDP), where an agent maintains a…

In the optimization of dynamical systems, the variables typically have constraints. Such problems can be modeled as a constrained Markov Decision Process (CMDP). This paper considers a model-free approach to the problem, where the…

Machine Learning · Computer Science 2021-02-02 Qinbo Bai , Vaneet Aggarwal , Ather Gattami

Accelerating exploration in visual reinforcement learning under sparse rewards remains challenging due to the substantial task-irrelevant variations. Despite advances in intrinsic exploration, many methods either assume access to…

Artificial Intelligence · Computer Science 2026-02-24 Dayang Liang , Ruihan Liu , Lipeng Wan , Yunlong Liu , Bo An

We use a simulation study to compare three methods for adaptive experimentation: Thompson sampling, Tempered Thompson sampling, and Exploration sampling. We gauge the performance of each in terms of social welfare and estimation accuracy,…

Methodology · Statistics 2022-07-05 Samantha Horn , Sabina J. Sloman

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

Reinforcement Learning algorithms that learn from human feedback (RLHF) need to be efficient in terms of statistical complexity, computational complexity, and query complexity. In this work, we consider the RLHF setting where the feedback…

Machine Learning · Computer Science 2024-03-14 Runzhe Wu , Wen Sun