English
Related papers

Related papers: Span-Based Optimal Sample Complexity for Average R…

200 papers

We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation. Using the optimism principle and assuming that the MDP has a linear structure, we…

Machine Learning · Computer Science 2021-04-27 Chen-Yu Wei , Mehdi Jafarnia-Jahromi , Haipeng Luo , Rahul Jain

This paper investigates the optimization problem of an infinite stage discrete time Markov decision process (MDP) with a long-run average metric considering both mean and variance of rewards together. Such performance metric is important…

Optimization and Control · Mathematics 2020-08-11 Li Xia

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

We establish an optimal sample complexity of $O(\epsilon^{-2})$ for obtaining an $\epsilon$-optimal global policy using a single-timescale actor-critic (AC) algorithm in infinite-horizon discounted Markov decision processes (MDPs) with…

Machine Learning · Computer Science 2026-05-08 Navdeep Kumar , Tehila Dahan , Lior Cohen , Ananyabrata Barua , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor

We study the sample complexity of learning an $\epsilon$-optimal policy in the Stochastic Shortest Path (SSP) problem. We first derive sample complexity bounds when the learner has access to a generative model. We show that there exists a…

Machine Learning · Computer Science 2022-10-12 Liyu Chen , Andrea Tirinzoni , Matteo Pirotta , Alessandro Lazaric

We investigate the problem of best-policy identification in discounted Markov Decision Processes (MDPs) when the learner has access to a generative model. The objective is to devise a learning algorithm returning the best policy as early as…

Machine Learning · Statistics 2021-05-11 Aymen Al Marjani , Alexandre Proutiere

We show subexponential lower bounds (i.e., $2^{\Omega (n^c)}$) on the smoothed complexity of the classical Howard's Policy Iteration algorithm for Markov Decision Processes. The bounds hold for the total reward and the average reward…

Computational Complexity · Computer Science 2022-12-02 Miranda Christ , Mihalis Yannakakis

In recent years, significant attention has been directed towards learning average-reward Markov Decision Processes (MDPs). However, existing algorithms either suffer from sub-optimal regret guarantees or computational inefficiencies. In…

Machine Learning · Computer Science 2024-06-04 Victor Boone , Zihan Zhang

We consider infinite-horizon $\gamma$-discounted (linear) constrained Markov decision processes (CMDPs) where the objective is to find a policy that maximizes the expected cumulative reward subject to expected cumulative constraints. Given…

Machine Learning · Computer Science 2025-10-29 Xingtu Liu , Lin F. Yang , Sharan Vaswani

Given a Markov Decision Process (MDP) with $n$ states and a totalnumber $m$ of actions, we study the number of iterations needed byPolicy Iteration (PI) algorithms to converge to the optimal$\gamma$-discounted policy. We consider two…

Optimization and Control · Mathematics 2016-02-11 Bruno Scherrer

Robust reinforcement learning (RL) under the average-reward criterion is essential for long-term decision-making, particularly when the environment may differ from its specification. However, a significant gap exists in understanding the…

Machine Learning · Computer Science 2025-09-26 Zachary Roch , Chi Zhang , George Atia , Yue Wang

We study the $(\varepsilon, \delta)$-PAC policy identification problem in finite-horizon episodic Markov Decision Processes. Existing approaches provide finite-time guarantees for approximate settings ($\varepsilon>0$) but suffer from high…

Machine Learning · Computer Science 2026-05-06 Cyrille Kone , Kevin Jamieson

This paper presents a systematic study on gap-dependent sample complexity in offline reinforcement learning. Prior work showed when the density ratio between an optimal policy and the behavior policy is upper bounded (the optimal policy…

Machine Learning · Computer Science 2022-08-05 Xinqi Wang , Qiwen Cui , Simon S. Du

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 consider a constrained Markov Decision Problem (CMDP) where the goal of an agent is to maximize the expected discounted sum of rewards over an infinite horizon while ensuring that the expected discounted sum of costs exceeds a certain…

Machine Learning · Computer Science 2024-11-01 Washim Uddin Mondal , Vaneet Aggarwal

In this paper, we study a mean-variance optimization problem in an infinite horizon discrete time discounted Markov decision process (MDP). The objective is to minimize the variance of system rewards with the constraint of mean performance.…

Optimization and Control · Mathematics 2017-08-24 Li Xia

In reward-free reinforcement learning (RL), an agent explores the environment first without any reward information, in order to achieve certain learning goals afterwards for any given reward. In this paper we focus on reward-free RL under…

Machine Learning · Computer Science 2023-03-21 Yuan Cheng , Ruiquan Huang , Jing Yang , Yingbin Liang

Several recent works have proposed instance-dependent upper bounds on the number of episodes needed to identify, with probability $1-\delta$, an $\varepsilon$-optimal policy in finite-horizon tabular Markov Decision Processes (MDPs). These…

Machine Learning · Statistics 2023-11-13 Aymen Al-Marjani , Andrea Tirinzoni , Emilie Kaufmann

We study a class of infinite-horizon average-cost Markov Decision Processes (MDPs) whose reward and transition structures are nearly separable. For the totally separable baseline (that is, with no perturbation), we derive an explicit…

Optimization and Control · Mathematics 2025-10-28 Dhairya Kantawala

In offline reinforcement learning (RL), the absence of active exploration calls for attention on the model robustness to tackle the sim-to-real gap, where the discrepancy between the simulated and deployed environments can significantly…

Machine Learning · Computer Science 2024-06-28 He Wang , Laixi Shi , Yuejie Chi