English
Related papers

Related papers: Quantum Computing Provides Exponential Regret Impr…

200 papers

We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions, where states are scalar-valued and running control rewards are absent but volatilities of the state processes depend…

Machine Learning · Computer Science 2025-07-25 Yilie Huang , Yanwei Jia , Xun Yu Zhou

In many modern applications, a system must dynamically choose between several adaptive learning algorithms that are trained online. Examples include model selection in streaming environments, switching between trading strategies in finance,…

Machine Learning · Computer Science 2026-01-19 Ilgam Latypov , Alexandra Suvorikova , Alexey Kroshnin , Alexander Gasnikov , Yuriy Dorn

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in…

Machine Learning · Computer Science 2023-06-05 Yan Dai , Haipeng Luo , Chen-Yu Wei , Julian Zimmert

While Bayesian-based exploration often demonstrates superior empirical performance compared to bonus-based methods in model-based reinforcement learning (RL), its theoretical understanding remains limited for model-free settings. Existing…

Machine Learning · Computer Science 2026-02-05 He Wang , Xingyu Xu , Yuejie Chi

Bandits with knapsacks (BwK) constitute a fundamental model that combines aspects of stochastic integer programming with online learning. Classical algorithms for BwK with a time horizon $T$ achieve a problem-independent regret bound of…

Quantum Physics · Physics 2025-07-08 Yuexin Su , Ziyi Yang , Peiyuan Huang , Tongyang Li , Yinyu Ye

We consider the problem of provably optimal exploration in reinforcement learning for finite horizon MDPs. We show that an optimistic modification to value iteration achieves a regret bound of $\tilde{O}( \sqrt{HSAT} + H^2S^2A+H\sqrt{T})$…

Machine Learning · Statistics 2017-07-04 Mohammad Gheshlaghi Azar , Ian Osband , Rémi Munos

Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqrt{T}$-type regret in the unregularized setting. However, the…

Machine Learning · Computer Science 2026-03-03 Kaixuan Ji , Qingyue Zhao , Heyang Zhao , Qiwei Di , Quanquan Gu

Upper Confidence Bound (UCB) algorithms are a widely-used class of sequential algorithms for the $K$-armed bandit problem. Despite extensive research over the past decades aimed at understanding their asymptotic and (near) minimax…

Statistics Theory · Mathematics 2024-12-10 Qiyang Han , Koulik Khamaru , Cun-Hui Zhang

Reinforcement learning (RL) with linear function approximation has received increasing attention recently. However, existing work has focused on obtaining $\sqrt{T}$-type regret bound, where $T$ is the number of interactions with the MDP.…

Machine Learning · Computer Science 2021-02-19 Jiafan He , Dongruo Zhou , Quanquan Gu

We present an algorithm based on the \emph{Optimism in the Face of Uncertainty} (OFU) principle which is able to learn Reinforcement Learning (RL) modeled by Markov decision process (MDP) with finite state-action space efficiently. By…

Machine Learning · Computer Science 2020-01-01 Zihan Zhang , Xiangyang Ji

In an episodic Markov Decision Process (MDP) problem, an online algorithm chooses from a set of actions in a sequence of $H$ trials, where $H$ is the episode length, in order to maximize the total payoff of the chosen actions. Q-learning,…

Machine Learning · Computer Science 2019-07-11 Xu Zhu

Gaussian process upper confidence bound (GP-UCB) is a theoretically established algorithm for Bayesian optimization (BO), where we assume the objective function $f$ follows a GP. One notable drawback of GP-UCB is that the theoretical…

Machine Learning · Computer Science 2025-11-10 Shion Takeno , Yu Inatsu , Masayuki Karasuyama

We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high probability. We introduce an algorithm, Cert-LSVI-UCB, for…

Machine Learning · Computer Science 2024-12-13 Weitong Zhang , Zhiyuan Fan , Jiafan He , Quanquan Gu

We present regret minimization algorithms for the contextual multi-armed bandit (CMAB) problem over $K$ actions in the presence of delayed feedback, a scenario where loss observations arrive with delays chosen by an adversary. As a…

Machine Learning · Computer Science 2025-10-13 Orin Levy , Liad Erez , Alon Cohen , Yishay Mansour

By leveraging the representation power of deep neural networks, neural upper confidence bound (UCB) algorithms have shown success in contextual bandits. To further balance the exploration and exploitation, we propose…

Machine Learning · Computer Science 2025-03-12 Ha Manh Bui , Enrique Mallada , Anqi Liu

We consider the problem of learning in episodic finite-horizon Markov decision processes with an unknown transition function, bandit feedback, and adversarial losses. We propose an efficient algorithm that achieves…

Machine Learning · Computer Science 2020-11-03 Chi Jin , Tiancheng Jin , Haipeng Luo , Suvrit Sra , Tiancheng Yu

Multi-arm bandit (MAB) and stochastic linear bandit (SLB) are important models in reinforcement learning, and it is well-known that classical algorithms for bandits with time horizon $T$ suffer $\Omega(\sqrt{T})$ regret. In this paper, we…

Machine Learning · Computer Science 2022-05-31 Zongqi Wan , Zhijie Zhang , Tongyang Li , Jialin Zhang , Xiaoming Sun

We study privacy-preserving exploration in sequential decision-making for environments that rely on sensitive data such as medical records. In particular, we focus on solving the problem of reinforcement learning (RL) subject to the…

Machine Learning · Computer Science 2022-06-24 Dung Daniel Ngo , Giuseppe Vietri , Zhiwei Steven Wu

Recently, model-free reinforcement learning has attracted research attention due to its simplicity, memory and computation efficiency, and the flexibility to combine with function approximation. In this paper, we propose Exploration…

Machine Learning · Computer Science 2020-12-10 Mehdi Jafarnia-Jahromi , Chen-Yu Wei , Rahul Jain , Haipeng Luo

We study the $K$-armed contextual dueling bandit problem, a sequential decision making setting in which the learner uses contextual information to make two decisions, but only observes \emph{preference-based feedback} suggesting that one…

Machine Learning · Computer Science 2021-11-25 Aadirupa Saha , Akshay Krishnamurthy