English
Related papers

Related papers: Q-Learning with Fine-Grained Gap-Dependent Regret

200 papers

Consider the sequential optimization of an expensive to evaluate and possibly non-convex objective function $f$ from noisy feedback, that can be considered as a continuum-armed bandit problem. Upper bounds on the regret performance of…

Machine Learning · Statistics 2021-03-11 Sattar Vakili , Kia Khezeli , Victor Picheny

Bayesian Optimization (BO) is widely used for optimising black-box functions but requires us to specify the length scale hyperparameter, which defines the smoothness of the functions the optimizer will consider. Most current BO algorithms…

Machine Learning · Statistics 2024-11-26 Juliusz Ziomek , Masaki Adachi , Michael A. Osborne

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

The contextual combinatorial semi-bandit problem with linear payoff functions is a decision-making problem in which a learner chooses a set of arms with the feature vectors in each round under given constraints so as to maximize the sum of…

Heavy-tailed distributions naturally arise in several settings, from finance to telecommunications. While regret minimization under subgaussian or bounded rewards has been widely studied, learning with heavy-tailed distributions only gained…

Machine Learning · Computer Science 2024-02-13 Gianmarco Genalti , Lupo Marsigli , Nicola Gatti , Alberto Maria Metelli

Autoregressive processes naturally arise in a large variety of real-world scenarios, including stock markets, sales forecasting, weather prediction, advertising, and pricing. When facing a sequential decision-making problem in such a…

We study variance-dependent regret bounds for Markov decision processes (MDPs). Algorithms with variance-dependent regret guarantees can automatically exploit environments with low variance (e.g., enjoying constant regret on deterministic…

Machine Learning · Computer Science 2023-05-23 Runlong Zhou , Zihan Zhang , Simon S. Du

Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS…

Machine Learning · Computer Science 2015-03-13 Niranjan Srinivas , Andreas Krause , Sham M. Kakade , Matthias Seeger

We study best-arm identification (BAI) in the fixed-budget setting. Adaptive allocations based on upper confidence bounds (UCBs), such as UCBE, are known to work well in BAI. However, it is well-known that its optimal regret is…

Machine Learning · Computer Science 2024-10-24 Rong J. B. Zhu , Yanqi Qiu

We study lifelong reinforcement learning (RL) in a regret minimization setting of linear contextual Markov decision process (MDP), where the agent needs to learn a multi-task policy while solving a streaming sequence of tasks. We propose an…

Machine Learning · Computer Science 2022-06-02 Sanae Amani , Lin F. Yang , Ching-An Cheng

We present an extensive study of the key problem of online learning where algorithms are allowed to abstain from making predictions. In the adversarial setting, we show how existing online algorithms and guarantees can be adapted to this…

Machine Learning · Computer Science 2019-11-15 Corinna Cortes , Giulia DeSalvo , Claudio Gentile , Mehryar Mohri , Scott Yang

This paper presents the first non-asymptotic result showing that a model-free algorithm can achieve a logarithmic cumulative regret for episodic tabular reinforcement learning if there exists a strictly positive sub-optimality gap in the…

Machine Learning · Computer Science 2021-02-24 Kunhe Yang , Lin F. Yang , Simon S. Du

We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves…

Machine Learning · Computer Science 2019-12-12 Aristide Tossou , Debabrota Basu , Christos Dimitrakakis

We study linear bandits when the underlying reward function is not linear. Existing work relies on a uniform misspecification parameter $\epsilon$ that measures the sup-norm error of the best linear approximation. This results in an…

Machine Learning · Computer Science 2023-07-21 Chong Liu , Ming Yin , Yu-Xiang Wang

We study the tail behavior of regret in stochastic multi-armed bandits for algorithms that are asymptotically optimal in expectation. While minimizing expected regret is the classical objective, recent work shows that even such algorithms…

Information Theory · Computer Science 2026-04-17 Subhodip Panda , Shubhada Agrawal

We study an important variant of the stochastic multi-armed bandit (MAB) problem, which takes penalization into consideration. Instead of directly maximizing cumulative expected reward, we need to balance between the total reward and…

Machine Learning · Statistics 2022-11-16 Guanhua Fang , Ping Li , Gennady Samorodnitsky

Contextual bandits are a rich model for sequential decision making given side information, with important applications, e.g., in recommender systems. We propose novel algorithms for contextual bandits harnessing neural networks to…

Machine Learning · Statistics 2022-03-01 Parnian Kassraie , Andreas Krause

A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to constraints, and then observes stochastic weights of these items and receives their sum as…

Machine Learning · Computer Science 2017-06-08 Branislav Kveton , Zheng Wen , Azin Ashkan , Csaba Szepesvari

We present the first gap-dependent analysis of regret and communication cost for on-policy federated $Q$-Learning in tabular episodic finite-horizon Markov decision processes (MDPs). Existing FRL methods focus on worst-case scenarios,…

Machine Learning · Statistics 2025-09-19 Haochen Zhang , Zhong Zheng , Lingzhou Xue

To tackle long planning horizon problems in reinforcement learning with general function approximation, we propose the first algorithm, termed as UCRL-WVTR, that achieves both \emph{horizon-free} and \emph{instance-dependent}, since it…

Machine Learning · Computer Science 2023-12-08 Jiayi Huang , Han Zhong , Liwei Wang , Lin F. Yang