English
Related papers

Related papers: A Provably Efficient Model-Free Posterior Sampling…

200 papers

Linear Temporal Logic (LTL) is widely used to specify high-level objectives for system policies, and it is highly desirable for autonomous systems to learn the optimal policy with respect to such specifications. However, learning the…

Machine Learning · Computer Science 2023-10-26 Daqian Shao , Marta Kwiatkowska

Bandit algorithms sequentially accumulate data using adaptive sampling policies, offering flexibility for real-world applications. However, excessive sampling can be costly, motivating the devolopment of early stopping methods and reliable…

Statistics Theory · Mathematics 2025-02-06 Zihan Cui

Thompson sampling (TS) is a powerful and widely used strategy for sequential decision-making, with applications ranging from Bayesian optimization to reinforcement learning (RL). Despite its success, the theoretical foundations of TS remain…

Machine Learning · Computer Science 2025-10-24 Jasmine Bayrooti , Sattar Vakili , Amanda Prorok , Carl Henrik Ek

Despite remarkable successes, deep reinforcement learning algorithms remain sample inefficient: they require an enormous amount of trial and error to find good policies. Model-based algorithms promise sample efficiency by building an…

Machine Learning · Computer Science 2023-05-19 Remo Sasso , Michelangelo Conserva , Paulo Rauber

We consider the adversarial linear contextual bandit problem, where the loss vectors are selected fully adversarially and the per-round action set (i.e. the context) is drawn from a fixed distribution. Existing methods for this problem…

Machine Learning · Computer Science 2023-09-06 Haolin Liu , Chen-Yu Wei , Julian Zimmert

We present a modular approach to reinforcement learning that uses a Bayesian representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set), drives exploration by sampling multiple models from the posterior and…

Machine Learning · Computer Science 2012-05-14 John Asmuth , Lihong Li , Michael L. Littman , Ali Nouri , David Wingate

In this work we first show that the classical Thompson sampling algorithm for multi-arm bandits is differentially private as-is, without any modification. We provide per-round privacy guarantees as a function of problem parameters and show…

Machine Learning · Computer Science 2024-07-23 Tingting Ou , Marco Avella Medina , Rachel Cummings

We study the performance of the Thompson Sampling algorithm for logistic bandit problems. In this setting, an agent receives binary rewards with probabilities determined by a logistic function, $\exp(\beta \langle a, \theta…

Machine Learning · Statistics 2025-02-21 Amaury Gouverneur , Borja Rodríguez-Gálvez , Tobias J. Oechtering , Mikael Skoglund

We study a cooperative multi-agent multi-armed bandits with M agents and K arms. The goal of the agents is to minimized the cumulative regret. We adapt a traditional Thompson Sampling algoirthm under the distributed setting. However, with…

Artificial Intelligence · Computer Science 2021-09-10 Jing Dong , Tan Li , Shaolei Ren , Linqi Song

In this paper we propose a general methodology to derive regret bounds for randomized multi-armed bandit algorithms. It consists in checking a set of sufficient conditions on the sampling probability of each arm and on the family of…

Machine Learning · Computer Science 2024-11-14 Dorian Baudry , Kazuya Suzuki , Junya Honda

Thompson Sampling has been demonstrated in many complex bandit models, however the theoretical guarantees available for the parametric multi-armed bandit are still limited to the Bernoulli case. Here we extend them by proving asymptotic…

Machine Learning · Statistics 2013-07-15 Nathaniel Korda , Emilie Kaufmann , Remi Munos

This paper is motivated by recent research in the $d$-dimensional stochastic linear bandit literature, which has revealed an unsettling discrepancy: algorithms like Thompson sampling and Greedy demonstrate promising empirical performance,…

Machine Learning · Computer Science 2025-05-20 Yuwei Luo , Mohsen Bayati

The problem of two-sided matching markets has a wide range of real-world applications and has been extensively studied in the literature. A line of recent works have focused on the problem setting where the preferences of one-side market…

Machine Learning · Computer Science 2022-05-03 Fang Kong , Junming Yin , Shuai Li

This paper unifies the design and the analysis of risk-averse Thompson sampling algorithms for the multi-armed bandit problem for a class of risk functionals $\rho$ that are continuous and dominant. We prove generalised concentration bounds…

Machine Learning · Computer Science 2022-04-19 Joel Q. L. Chang , Vincent Y. F. Tan

Any reinforcement learning algorithm that applies to all Markov decision processes (MDPs) will suffer $\Omega(\sqrt{SAT})$ regret on some MDP, where $T$ is the elapsed time and $S$ and $A$ are the cardinalities of the state and action…

Machine Learning · Statistics 2014-11-04 Ian Osband , Benjamin Van Roy

We consider model selection for classic Reinforcement Learning (RL) environments -- Multi Armed Bandits (MABs) and Markov Decision Processes (MDPs) -- under general function approximations. In the model selection framework, we do not know…

Machine Learning · Statistics 2022-07-08 Avishek Ghosh , Sayak Ray Chowdhury

We propose a simple model selection approach for algorithms in stochastic bandit and reinforcement learning problems. As opposed to prior work that (implicitly) assumes knowledge of the optimal regret, we only require that each base…

Machine Learning · Computer Science 2020-12-25 Aldo Pacchiano , Christoph Dann , Claudio Gentile , Peter Bartlett

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

Thompson sampling (TS) has emerged as a robust technique for contextual bandit problems. However, TS requires posterior inference and optimization for action generation, prohibiting its use in many online platforms where latency and ease of…

Machine Learning · Computer Science 2024-07-23 Hongseok Namkoong , Samuel Daulton , Eytan Bakshy

In this paper, we study the problem of regret minimization for episodic Reinforcement Learning (RL) both in the model-free and the model-based setting. We focus on learning with general function classes and general model classes, and we…

Machine Learning · Computer Science 2022-03-04 Grigoris Velegkas , Zhuoran Yang , Amin Karbasi