English
Related papers

Related papers: Deep Bandits Show-Off: Simple and Efficient Explor…

200 papers

Fully Bayesian approaches to sequential decision-making assume that problem parameters are generated from a known prior. In practice, such information is often lacking. This problem is exacerbated in setups with partial information, where a…

Machine Learning · Statistics 2022-08-08 Amit Peleg , Naama Pearl , Ron Meir

Uncertainty quantification is a critical aspect of reinforcement learning and deep learning, with numerous applications ranging from efficient exploration and stable offline reinforcement learning to outlier detection in medical…

Machine Learning · Computer Science 2025-03-27 Moritz A. Zanger , Pascal R. Van der Vaart , Wendelin Böhmer , Matthijs T. J. Spaan

Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of the learning algorithm correspond to important decisions…

Machine Learning · Computer Science 2018-01-11 Sampath Kannan , Jamie Morgenstern , Aaron Roth , Bo Waggoner , Zhiwei Steven Wu

Sample-average approximations (SAA) are a practical means of finding approximate solutions of stochastic programming problems involving an extremely large (or infinite) number of scenarios. SAA can also be used to find estimates of a lower…

Other Statistics · Statistics 2014-05-08 Jiajie Chen , Cong Han Lim , Peter Z. G. Qian , Jeff Linderoth , Stephen J. Wright

This paper studies the Bayesian regret of a variant of the Thompson-Sampling algorithm for bandit problems. It builds upon the information-theoretic framework of [Russo and Van Roy, 2015] and, more specifically, on the rate-distortion…

Machine Learning · Statistics 2024-03-07 Amaury Gouverneur , Borja Rodríguez-Gálvez , Tobias J. Oechtering , Mikael Skoglund

The computational costs of inference and planning have confined Bayesian model-based reinforcement learning to one of two dismal fates: powerful Bayes-adaptive planning but only for simplistic models, or powerful, Bayesian non-parametric…

Artificial Intelligence · Computer Science 2014-02-11 Arthur Guez , David Silver , Peter Dayan

The Causal Bandit is a variant of the classic Bandit problem where an agent must identify the best action in a sequential decision-making process, where the reward distribution of the actions displays a non-trivial dependence structure that…

Artificial Intelligence · Computer Science 2022-09-30 Arnoud A. W. M. de Kroon , Danielle Belgrave , Joris M. Mooij

Bayesian optimization is a framework for global search via maximum a posteriori updates rather than simulated annealing, and has gained prominence for decision-making under uncertainty. In this work, we cast Bayesian optimization as a…

Machine Learning · Computer Science 2022-03-24 Amrit Singh Bedi , Dheeraj Peddireddy , Vaneet Aggarwal , Brian M. Sadler , Alec Koppel

Policy inference plays an essential role in the contextual bandit problem. In this paper, we use empirical likelihood to develop a Bayesian inference method for the joint analysis of multiple contextual bandit policies in finite sample…

Machine Learning · Statistics 2026-02-12 Jiangrong Ouyang , Mingming Gong , Howard Bondell

We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the Thompson sampling…

Machine Learning · Statistics 2021-11-01 Brendan O'Donoghue , Tor Lattimore

Contextual bandits are incredibly useful in many practical problems. We go one step further by devising a more realistic problem that combines: (1) contextual bandits with dense arm features, (2) non-linear reward functions, and (3) a…

Machine Learning · Computer Science 2026-03-18 Wei Min Loh , Sajib Kumer Sinha , Ankur Agarwal , Pascal Poupart

Thompson sampling provides a solution to bandit problems in which new observations are allocated to arms with the posterior probability that an arm is optimal. While sometimes easy to implement and asymptotically optimal, Thompson sampling…

Machine Learning · Computer Science 2014-10-16 Dean Eckles , Maurits Kaptein

We propose a novel framework for structured bandits, which we call an influence diagram bandit. Our framework captures complex statistical dependencies between actions, latent variables, and observations; and thus unifies and extends many…

Machine Learning · Computer Science 2020-07-10 Tong Yu , Branislav Kveton , Zheng Wen , Ruiyi Zhang , Ole J. Mengshoel

Meta-learning is characterized by its ability to learn how to learn, enabling the adaptation of learning strategies across different tasks. Recent research introduced the Meta-Thompson Sampling (Meta-TS), which meta-learns an unknown prior…

Machine Learning · Statistics 2024-09-12 Hao Li , Dong Liang , Zheng Xie

Evaluating the safety of frontier AI systems is an increasingly important concern, helping to measure the capabilities of such models and identify risks before deployment. However, it has been recognised that if AI agents are aware that…

Machine Learning · Computer Science 2025-10-01 Joel Dyer , Daniel Jarne Ornia , Nicholas Bishop , Anisoara Calinescu , Michael Wooldridge

We consider the neural contextual bandit problem. In contrast to the existing work which primarily focuses on ReLU neural nets, we consider a general set of smooth activation functions. Under this more general setting, (i) we derive…

Machine Learning · Statistics 2022-06-02 Sudeep Salgia , Sattar Vakili , Qing Zhao

Bayesian optimization (BO) is a powerful framework for estimating parameters of expensive simulation models, particularly in settings where the likelihood is intractable and evaluations are costly. In stochastic models every simulation is…

We address online combinatorial optimization when the player has a prior over the adversary's sequence of losses. In this framework, Russo and Van Roy proposed an information-theoretic analysis of Thompson Sampling based on the information…

Machine Learning · Computer Science 2022-04-05 Sébastien Bubeck , Mark Sellke

The stochastic multi-armed bandit (MAB) problem is one of the most fundamental models in sequential decision-making, with the core challenge being the trade-off between exploration and exploitation. Although algorithms such as Upper…

Machine Learning · Computer Science 2025-10-13 Di Zhang

We propose a new bootstrap-based online algorithm for stochastic linear bandit problems. The key idea is to adopt residual bootstrap exploration, in which the agent estimates the next step reward by re-sampling the residuals of mean reward…

Machine Learning · Statistics 2022-06-20 Shuang Wu , Chi-Hua Wang , Yuantong Li , Guang Cheng