English
Related papers

Related papers: Regret Bounds for Thompson Sampling in Episodic Re…

200 papers

This paper studies bandit problems where an agent has access to offline data that might be utilized to potentially improve the estimation of each arm's reward distribution. A major obstacle in this setting is the existence of compound…

Machine Learning · Computer Science 2023-12-21 Wen Huang , Xintao Wu

Algorithm selection is typically based on models of algorithm performance, learned during a separate offline training sequence, which can be prohibitively expensive. In recent work, we adopted an online approach, in which a performance…

Artificial Intelligence · Computer Science 2013-01-31 Matteo Gagliolo , Juergen Schmidhuber

We consider minimisation of dynamic regret in non-stationary bandits with a slowly varying property. Namely, we assume that arms' rewards are stochastic and independent over time, but that the absolute difference between the expected…

Machine Learning · Computer Science 2021-10-26 Ramakrishnan Krishnamurthy , Aditya Gopalan

This paper investigates stochastic and adversarial combinatorial multi-armed bandit problems. In the stochastic setting under semi-bandit feedback, we derive a problem-specific regret lower bound, and discuss its scaling with the dimension…

Machine Learning · Computer Science 2015-11-09 Richard Combes , M. Sadegh Talebi , Alexandre Proutiere , Marc Lelarge

We study the asymptotic performance of the Thompson sampling algorithm in the batched multi-armed bandit setting where the time horizon $T$ is divided into batches, and the agent is not able to observe the rewards of her actions until the…

Machine Learning · Computer Science 2021-10-04 Cem Kalkanli , Ayfer Ozgur

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

A latent bandit problem is one in which the learning agent knows the arm reward distributions conditioned on an unknown discrete latent state. The primary goal of the agent is to identify the latent state, after which it can act optimally.…

Machine Learning · Computer Science 2020-06-17 Joey Hong , Branislav Kveton , Manzil Zaheer , Yinlam Chow , Amr Ahmed , Craig Boutilier

We study finite-armed semiparametric bandits, where each arm's reward combines a linear component with an unknown, potentially adversarial shift. This model strictly generalizes classical linear bandits and reflects complexities common in…

Machine Learning · Statistics 2025-06-18 Seok-Jin Kim , Gi-Soo Kim , Min-hwan Oh

We consider the problem of stochastic $K$-armed dueling bandit in the contextual setting, where at each round the learner is presented with a context set of $K$ items, each represented by a $d$-dimensional feature vector, and the goal of…

Machine Learning · Computer Science 2021-05-11 Aadirupa Saha , Aditya Gopalan

We exhibit optimal control strategies for a simple toy problem in which the underlying dynamics depend on a parameter that is initially unknown and must be learned. We consider a cost function posed over a finite time interval, in contrast…

Optimization and Control · Mathematics 2020-02-27 Charles L. Fefferman , Bernat Guillen Pegueroles , Clarence W. Rowley , Melanie Weber

Multi-armed bandit problems are the most basic examples of sequential decision problems with an exploration-exploitation trade-off. This is the balance between staying with the option that gave highest payoffs in the past and exploring new…

Machine Learning · Computer Science 2012-11-06 Sébastien Bubeck , Nicolò Cesa-Bianchi

We consider the problem of learning in single-player and multiplayer multiarmed bandit models. Bandit problems are classes of online learning problems that capture exploration versus exploitation tradeoffs. In a multiarmed bandit model,…

Machine Learning · Statistics 2016-12-02 Naumaan Nayyar , Dileep Kalathil , Rahul Jain

We study nonparametric contextual bandits under batch constraints, where the expected reward for each action is modeled as a smooth function of covariates, and the policy updates are made at the end of each batch of observations. We…

Statistics Theory · Mathematics 2025-10-06 Rong Jiang , Cong Ma

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

Classic no-regret multi-armed bandit algorithms, including the Upper Confidence Bound (UCB), Hedge, and EXP3, are inherently unfair by design. Their unfairness stems from their objective of playing the most rewarding arm as frequently as…

Machine Learning · Computer Science 2024-05-14 Abhishek Sinha

Motivated by the challenges of edge inference, we study a variant of the cascade bandit model in which each arm corresponds to an inference model with an associated accuracy and error probability. We analyse four decision-making…

Machine Learning · Computer Science 2026-03-30 R Sri Prakash , Nikhil Karamchandani , Sharayu Moharir

Non-stationary multi-armed bandit (NS-MAB) problems have recently received significant attention. NS-MAB are typically modelled in two scenarios: abruptly changing, where reward distributions remain constant for a certain period and change…

Machine Learning · Computer Science 2023-05-23 Han Qi , Yue Wang , Li Zhu

In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of interest is regret, defined as the gap between the expected…

Optimization and Control · Mathematics 2010-11-23 Yi Gai , Bhaskar Krishnamachari , Rahul Jain

In the stochastic multi-armed bandit problem, a randomized probability matching policy called Thompson sampling (TS) has shown excellent performance in various reward models. In addition to the empirical performance, TS has been shown to…

Machine Learning · Computer Science 2023-02-06 Jongyeong Lee , Junya Honda , Chao-Kai Chiang , Masashi Sugiyama

In the multiarmed bandit problem a gambler chooses an arm of a slot machine to pull considering a tradeoff between exploration and exploitation. We study the stochastic bandit problem where each arm has a reward distribution supported in a…

Statistics Theory · Mathematics 2013-03-29 Junya Honda , Akimichi Takemura
‹ Prev 1 8 9 10 Next ›