English
Related papers

Related papers: Span-Agnostic Optimal Sample Complexity and Oracle…

200 papers

We provide an algorithm that achieves the optimal regret rate in an unknown weakly communicating Markov Decision Process (MDP). The algorithm proceeds in episodes where, in each episode, it picks a policy using regularization based on the…

Machine Learning · Computer Science 2012-05-14 Peter L. Bartlett , Ambuj Tewari

We propose an algorithm for deterministic continuous Markov Decision Processes with sparse rewards that computes the optimal policy exactly with no dependency on the size of the state space. The algorithm has time complexity of $O( |R|^3…

Machine Learning · Computer Science 2018-05-21 Joshua R. Bertram , Peng Wei

We consider the problem of designing a control policy for an infinite-horizon discounted cost Markov decision process $\mathcal{M}$ when we only have access to an approximate model $\hat{\mathcal{M}}$. How well does an optimal policy…

Optimization and Control · Mathematics 2024-02-15 Berk Bozkurt , Aditya Mahajan , Ashutosh Nayyar , Yi Ouyang

In this paper we consider the problem of computing an $\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any…

Optimization and Control · Mathematics 2019-06-07 Aaron Sidford , Mengdi Wang , Xian Wu , Lin F. Yang , Yinyu Ye

We study the optimal sample complexity in large-scale Reinforcement Learning (RL) problems with policy space generalization, i.e. the agent has a prior knowledge that the optimal policy lies in a known policy space. Existing results show…

Machine Learning · Computer Science 2020-08-18 Wenlong Mou , Zheng Wen , Xi Chen

We study offline reinforcement learning (RL) with linear MDPs under the infinite-horizon discounted setting which aims to learn a policy that maximizes the expected discounted cumulative reward using a pre-collected dataset. Existing…

Machine Learning · Statistics 2024-06-04 Kihyuk Hong , Ambuj Tewari

We consider a step search method for continuous optimization under a stochastic setting where the function values and gradients are available only through inexact probabilistic zeroth- and first-order oracles. Unlike the stochastic gradient…

Optimization and Control · Mathematics 2023-11-03 Billy Jin , Katya Scheinberg , Miaolan Xie

We develop a novel and single-loop variance-reduced algorithm to solve a class of stochastic nonconvex-convex minimax problems involving a nonconvex-linear objective function, which has various applications in different fields such as…

Optimization and Control · Mathematics 2020-10-27 Quoc Tran-Dinh , Deyi Liu , Lam M. Nguyen

In this paper, we revisit the smooth and strongly-convex-strongly-concave minimax optimization problem. Zhang et al. (2021) and Ibrahim et al. (2020) established the lower bound $\Omega\left(\sqrt{\kappa_x\kappa_y} \log…

Optimization and Control · Mathematics 2022-05-12 Dmitry Kovalev , Alexander Gasnikov

We consider online learning when the time horizon is unknown. We apply a minimax analysis, beginning with the fixed horizon case, and then moving on to two unknown-horizon settings, one that assumes the horizon is chosen randomly according…

Machine Learning · Computer Science 2013-10-08 Haipeng Luo , Robert E. Schapire

Subsampling is a popular approach to alleviating the computational burden for analyzing massive datasets. Recent efforts have been devoted to various statistical models without explicit regularization. In this paper, we develop an efficient…

Methodology · Statistics 2022-04-12 Yunlu Chen , Nan Zhang

We consider the estimation of a regression function with random design and heteroscedastic noise in a nonparametric setting. More precisely, we address the problem of characterizing the optimal penalty when the regression function is…

Statistics Theory · Mathematics 2015-06-29 Adrien Saumard

In this paper, we study the fundamental open question of finding the optimal high-order algorithm for solving smooth convex minimization problems. Arjevani et al. (2019) established the lower bound $\Omega\left(\epsilon^{-2/(3p+1)}\right)$…

Optimization and Control · Mathematics 2022-05-20 Dmitry Kovalev , Alexander Gasnikov

This paper addresses the poor finite-horizon performance of existing online \emph{restless bandit} (RB) algorithms, which stems from the prohibitive sample complexity of learning a full \emph{Markov decision process} (MDP) for each agent.…

Machine Learning · Computer Science 2026-04-07 Jiamin Xu , Ivan Nazarov , Aditya Rastogi , África Periáñez , Kyra Gan

Offline reinforcement learning (RL) aims to find an optimal policy for Markov decision processes (MDPs) using a pre-collected dataset. In this work, we revisit the linear programming (LP) reformulation of Markov decision processes for…

Machine Learning · Computer Science 2024-12-11 Asuman Ozdaglar , Sarath Pattathil , Jiawei Zhang , Kaiqing Zhang

We study average-reward Markov decision processes (AMDPs) and develop novel first-order methods with strong theoretical guarantees for both policy optimization and policy evaluation. Compared with intensive research efforts in finite sample…

Machine Learning · Computer Science 2024-10-01 Tianjiao Li , Feiyang Wu , Guanghui Lan

We address the problem of density estimation with $\mathbb{L}_s$-loss by selection of kernel estimators. We develop a selection procedure and derive corresponding $\mathbb{L}_s$-risk oracle inequalities. It is shown that the proposed…

Statistics Theory · Mathematics 2012-11-26 Alexander Goldenshluger , Oleg Lepski

Sparse reduced rank regression is an essential statistical learning method. In the contemporary literature, estimation is typically formulated as a nonconvex optimization that often yields to a local optimum in numerical computation. Yet,…

Methodology · Statistics 2022-12-06 Canhong Wen , Ruipeng Dong , Xueqin Wang , Weiyu Li , Heping Zhang

We study safe reinforcement learning in finite-horizon linear mixture constrained Markov decision processes (CMDPs) with adversarial rewards under full-information feedback and an unknown transition kernel. We propose a primal-dual policy…

Machine Learning · Computer Science 2026-03-31 Kihyun Yu , Seoungbin Bae , Dabeen Lee

This paper initiates the study of scale-free learning in Markov Decision Processes (MDPs), where the scale of rewards/losses is unknown to the learner. We design a generic algorithmic framework, \underline{S}cale \underline{C}lipping…

Machine Learning · Computer Science 2024-03-05 Mingyu Chen , Xuezhou Zhang