English
Related papers

Related papers: Finite-Time Bounds for Average-Reward Fitted Q-Ite…

200 papers

This paper presents new variants of the averaged alternating modified reflections (AAMR) method for the best approximation problem. Under a mild constraint qualification, we first show its weak convergence and then establish a convergence…

Optimization and Control · Mathematics 2016-09-06 Shin-ya Matsushita

This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear Markov decision processes (MDPs) and linear mixture MDPs under the Bellman optimality condition. While guaranteeing computational…

Machine Learning · Computer Science 2024-09-25 Woojin Chae , Dabeen Lee

Reinforcement Learning (RL) has emerged as a mainstream paradigm for training Mobile GUI Agents, yet it struggles with the temporal credit assignment problem inherent in long-horizon tasks. A primary challenge lies in the trade-off between…

This paper develops a novel control-theoretic framework to analyze the non-asymptotic convergence of Q-learning. We show that the dynamics of asynchronous Q-learning with a constant step-size can be naturally formulated as a discrete-time…

Optimization and Control · Mathematics 2024-08-23 Donghwan Lee , Jianghai Hu , Niao He

We study offline reinforcement learning under $Q^\star$-approximation and partial coverage, a setting that motivates practical algorithms such as Conservative $Q$-Learning (CQL; Kumar et al., 2020) but has received limited theoretical…

Machine Learning · Computer Science 2026-02-13 Haolin Liu , Braham Snyder , Chen-Yu Wei

We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm when combined with tail-averaging. We derive finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice…

Machine Learning · Computer Science 2024-09-20 Gandharv Patil , Prashanth L. A. , Dheeraj Nagaraj , Doina Precup

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

Model-free reinforcement learning algorithms combined with value function approximation have recently achieved impressive performance in a variety of application domains. However, the theoretical understanding of such algorithms is limited,…

Machine Learning · Computer Science 2021-02-12 Botao Hao , Nevena Lazic , Yasin Abbasi-Yadkori , Pooria Joulani , Csaba Szepesvari

We consider online reinforcement learning (RL) in episodic Markov decision processes (MDPs) under the linear $q^\pi$-realizability assumption, where it is assumed that the action-values of all policies can be expressed as linear functions…

Machine Learning · Computer Science 2023-12-21 Gellért Weisz , András György , Csaba Szepesvári

We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces, where data are generated online from a single trajectory under a Markovian behavior policy. To avoid maintaining an…

Machine Learning · Computer Science 2026-03-05 Shengbo Wang

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

Incorporating high-level knowledge is an effective way to expedite reinforcement learning (RL), especially for complex tasks with sparse rewards. We investigate an RL problem where the high-level knowledge is in the form of reward machines,…

Artificial Intelligence · Computer Science 2022-02-10 Zhe Xu , Ivan Gavran , Yousef Ahmad , Rupak Majumdar , Daniel Neider , Ufuk Topcu , Bo Wu

Reinforcement learning (RL) for exponential-utility optimization in discounted Markov decision processes (MDPs) lacks principled value-based algorithms. We address this gap in the fixed risk-aversion setting. Building on the Bellman-type…

Machine Learning · Computer Science 2026-05-11 Gugan Thoppe , L. A. Prashanth , Ankur Naskar , Sanjay Bhat

Recently, there has been a surge of interest in analyzing the non-asymptotic behavior of model-free reinforcement learning algorithms. However, the performance of such algorithms in non-ideal environments, such as in the presence of…

Machine Learning · Computer Science 2024-09-06 Sreejeet Maity , Aritra Mitra

Inverse reinforcement learning (IRL) denotes a powerful family of algorithms for recovering a reward function justifying the behavior demonstrated by an expert agent. A well-known limitation of IRL is the ambiguity in the choice of the…

Machine Learning · Computer Science 2023-04-26 Alberto Maria Metelli , Filippo Lazzati , Marcello Restelli

We study regret minimization for infinite-horizon average-reward Markov Decision Processes (MDPs) under cost constraints. We start by designing a policy optimization algorithm with carefully designed action-value estimator and bonus term,…

Machine Learning · Computer Science 2022-02-02 Liyu Chen , Rahul Jain , Haipeng Luo

Studying how to fine-tune offline reinforcement learning (RL) pre-trained policy is profoundly significant for enhancing the sample efficiency of RL algorithms. However, directly fine-tuning pre-trained policies often results in sub-optimal…

Machine Learning · Computer Science 2024-05-29 Ziqi Zhang , Xiao Xiong , Zifeng Zhuang , Jinxin Liu , Donglin Wang

In this paper, we investigate the robustness of stationary mean-field equilibria in the presence of model uncertainties, specifically focusing on infinite-horizon discounted cost functions. To achieve this, we initially establish…

Systems and Control · Electrical Eng. & Systems 2026-04-10 Uğur Aydın , Naci Saldi

Processes (MDPs) often require frequent decision making, that is, taking an action every microsecond, second, or minute. Infinite horizon discount reward formulation is still relevant for a large portion of these applications, because…

Optimization and Control · Mathematics 2014-12-17 Yin-Lam Chow , Junjie Qin

We derive a new analysis of Follow The Regularized Leader (FTRL) for online learning with delayed bandit feedback. By separating the cost of delayed feedback from that of bandit feedback, our analysis allows us to obtain new results in…

Machine Learning · Computer Science 2023-05-16 Dirk van der Hoeven , Lukas Zierahn , Tal Lancewicki , Aviv Rosenberg , Nicoló Cesa-Bianchi
‹ Prev 1 3 4 5 6 7 10 Next ›