English
Related papers

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

200 papers

We study the gap-dependent bounds of two important algorithms for on-policy Q-learning for finite-horizon episodic tabular Markov Decision Processes (MDPs): UCB-Advantage (Zhang et al. 2020) and Q-EarlySettled-Advantage (Li et al. 2021).…

Machine Learning · Statistics 2025-03-11 Zhong Zheng , Haochen Zhang , Lingzhou Xue

This paper presents a new model-free algorithm for episodic finite-horizon Markov Decision Processes (MDP), Adaptive Multi-step Bootstrap (AMB), which enjoys a stronger gap-dependent regret bound. The first innovation is to estimate the…

Machine Learning · Computer Science 2021-07-05 Haike Xu , Tengyu Ma , Simon S. Du

We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$. We propose a model-free algorithm UCB-Advantage and prove that it…

Machine Learning · Computer Science 2020-06-09 Zihan Zhang , Yuan Zhou , Xiangyang Ji

We consider the problem of finitely parameterized multi-armed bandits where the model of the underlying stochastic environment can be characterized based on a common unknown parameter. The true parameter is unknown to the learning agent.…

Machine Learning · Computer Science 2020-11-10 Kishan Panaganti , Dileep Kalathil

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

Online reinforcement learning in infinite-horizon Markov decision processes (MDPs) remains less theoretically and algorithmically developed than its episodic counterpart, with many algorithms suffering from high ``burn-in'' costs and…

Machine Learning · Computer Science 2026-03-26 Guy Zamir , Matthew Zurek , Yudong Chen

We study gap-dependent performance guarantees for nearly minimax-optimal algorithms in reinforcement learning with linear function approximation. While prior works have established gap-dependent regret bounds in this setting, existing…

Machine Learning · Statistics 2026-02-25 Haochen Zhang , Zhong Zheng , Lingzhou Xue

We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the…

Machine Learning · Computer Science 2021-10-27 Christoph Dann , Teodor V. Marinov , Mehryar Mohri , Julian Zimmert

Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration…

Machine Learning · Statistics 2019-11-01 Botao Hao , Yasin Abbasi-Yadkori , Zheng Wen , Guang Cheng

Stochastic multi-armed bandits (MABs) provide a fundamental reinforcement learning model to study sequential decision making in uncertain environments. The upper confidence bounds (UCB) algorithm gave birth to the renaissance of bandit…

Machine Learning · Computer Science 2024-06-11 Ambrus Tamás , Szabolcs Szentpéteri , Balázs Csanád Csáji

We consider model-free reinforcement learning (RL) in non-stationary Markov decision processes. Both the reward functions and the state transition functions are allowed to vary arbitrarily over time as long as their cumulative variations do…

Machine Learning · Computer Science 2022-08-23 Weichao Mao , Kaiqing Zhang , Ruihao Zhu , David Simchi-Levi , Tamer Başar

In this paper, we study gap-dependent regret guarantees for risk-sensitive reinforcement learning based on the entropic risk measure. We propose a novel definition of sub-optimality gaps, which we call cascaded gaps, and we discuss their…

Machine Learning · Computer Science 2022-03-08 Yingjie Fei , Ruitu Xu

The multi-armed bandit (MAB) problem is a foundational framework in sequential decision-making under uncertainty, extensively studied for its applications in areas such as clinical trials, online advertising, and resource allocation.…

Machine Learning · Computer Science 2024-10-28 Ali Baheri

We propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new algorithm for reinforcement learning in tabular and possibly stage-dependent, episodic Markov decision process. UCBMQ is based on Q-learning where we add a momentum term…

Machine Learning · Statistics 2022-03-21 Pierre Menard , Omar Darwiche Domingues , Xuedong Shang , Michal Valko

In this paper, we investigate the problem of \textit{episodic reinforcement learning} with quantum oracles for state evolution. To this end, we propose an \textit{Upper Confidence Bound} (UCB) based quantum algorithmic framework to…

Machine Learning · Computer Science 2023-02-20 Bhargav Ganguly , Yulian Wu , Di Wang , Vaneet Aggarwal

In the kernelized bandit problem, a learner aims to sequentially compute the optimum of a function lying in a reproducing kernel Hilbert space given only noisy evaluations at sequentially chosen points. In particular, the learner aims to…

Machine Learning · Computer Science 2023-08-15 Justin Whitehouse , Zhiwei Steven Wu , Aaditya Ramdas

A fundamental question in reinforcement learning is whether model-free algorithms are sample efficient. Recently, Jin et al. \cite{jin2018q} proposed a Q-learning algorithm with UCB exploration policy, and proved it has nearly optimal…

Machine Learning · Computer Science 2019-09-30 Kefan Dong , Yuanhao Wang , Xiaoyu Chen , Liwei Wang

One of the key drivers of complexity in the classical (stochastic) multi-armed bandit (MAB) problem is the difference between mean rewards in the top two arms, also known as the instance gap. The celebrated Upper Confidence Bound (UCB)…

Machine Learning · Computer Science 2021-10-27 Anand Kalvit , Assaf Zeevi

I introduce and analyse an anytime version of the Optimally Confident UCB (OCUCB) algorithm designed for minimising the cumulative regret in finite-armed stochastic bandits with subgaussian noise. The new algorithm is simple, intuitive (in…

Machine Learning · Computer Science 2016-05-09 Tor Lattimore

We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature…

Machine Learning · Computer Science 2026-05-18 Rahul Singh , Siddharth Chandak , Eric Moulines , Vivek S. Borkar , Nicholas Bambos
‹ Prev 1 2 3 10 Next ›