中文
相关论文

相关论文: Global Convergence of Average Reward Constrained M…

200 篇论文

This paper investigates infinite-horizon average reward Constrained Markov Decision Processes (CMDPs) with general parametrization. We propose a Primal-Dual Natural Actor-Critic algorithm that adeptly manages constraints while ensuring a…

机器学习 · 计算机科学 2025-12-11 Yang Xu , Swetha Ganesh , Washim Uddin Mondal , Qinbo Bai , Vaneet Aggarwal

This paper explores the realm of infinite horizon average reward Constrained Markov Decision Processes (CMDPs). To the best of our knowledge, this work is the first to delve into the regret and constraint violation analysis of average…

机器学习 · 计算机科学 2024-10-31 Qinbo Bai , Washim Uddin Mondal , Vaneet Aggarwal

We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the unichain assumption and general policy parameterizations. Existing regret analyses for constrained reinforcement learning largely rely on…

机器学习 · 计算机科学 2026-02-10 Anirudh Satheesh , Vaneet Aggarwal

This work examines average-reward reinforcement learning with general policy parametrization. Existing state-of-the-art (SOTA) guarantees for this problem are either suboptimal or hindered by several challenges, including poor scalability…

机器学习 · 计算机科学 2025-05-07 Swetha Ganesh , Washim Uddin Mondal , Vaneet Aggarwal

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…

机器学习 · 计算机科学 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

We analyze the global convergence of the single-timescale actor-critic (AC) algorithm for the infinite-horizon discounted Markov Decision Processes (MDPs) with finite state spaces. To this end, we introduce an elegant analytical framework…

机器学习 · 计算机科学 2025-06-05 Navdeep Kumar , Priyank Agrawal , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor

We consider a discounted cost constrained Markov decision process (CMDP) policy optimization problem, in which an agent seeks to maximize a discounted cumulative reward subject to a number of constraints on discounted cumulative utilities.…

最优化与控制 · 数学 2024-11-21 Sihan Zeng , Thinh T. Doan , Justin Romberg

In this paper, we consider an infinite horizon average reward Markov Decision Process (MDP). Distinguishing itself from existing works within this context, our approach harnesses the power of the general policy gradient-based algorithm,…

机器学习 · 计算机科学 2024-02-06 Qinbo Bai , Washim Uddin Mondal , Vaneet Aggarwal

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…

机器学习 · 计算机科学 2024-11-01 Washim Uddin Mondal , Vaneet Aggarwal

We consider the problem of constrained Markov decision process (CMDP) in continuous state-actions spaces where the goal is to maximize the expected cumulative reward subject to some constraints. We propose a novel Conservative Natural…

机器学习 · 计算机科学 2024-05-20 Qinbo Bai , Amrit Singh Bedi , Vaneet Aggarwal

This paper focuses on learning a Constrained Markov Decision Process (CMDP) via general parameterized policies. We propose a Primal-Dual based Regularized Accelerated Natural Policy Gradient (PDR-ANPG) algorithm that uses entropy and…

机器学习 · 计算机科学 2026-05-04 Washim Uddin Mondal , Vaneet Aggarwal

Actor Critic methods have found immense applications on a wide range of Reinforcement Learning tasks especially when the state-action space is large. In this paper, we consider actor critic and natural actor critic algorithms with function…

机器学习 · 计算机科学 2025-09-01 Prashansa Panda , Shalabh Bhatnagar

We study the sequential decision making problem of maximizing the expected total reward while satisfying a constraint on the expected total utility. We employ the natural policy gradient method to solve the discounted infinite-horizon…

最优化与控制 · 数学 2025-10-16 Dongsheng Ding , Kaiqing Zhang , Jiali Duan , Tamer Başar , Mihailo R. Jovanović

We consider the reinforcement learning problem for partially observed Markov decision processes (POMDPs) with large or even countably infinite state spaces, where the controller has access to only noisy observations of the underlying…

机器学习 · 计算机科学 2023-07-20 Semih Cayci , Niao He , R. Srikant

We consider the problem of constrained Markov Decision Process (CMDP) where an agent interacts with a unichain Markov Decision Process. At every interaction, the agent obtains a reward. Further, there are $K$ cost functions. The agent aims…

机器学习 · 计算机科学 2022-06-22 Mridul Agarwal , Qinbo Bai , Vaneet Aggarwal

The problem of constrained Markov decision process (CMDP) is investigated, where an agent aims to maximize the expected accumulated discounted reward subject to multiple constraints on its utilities/costs. A new primal-dual approach is…

最优化与控制 · 数学 2021-10-22 Tianjiao Li , Ziwei Guan , Shaofeng Zou , Tengyu Xu , Yingbin Liang , Guanghui Lan

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

机器学习 · 计算机科学 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

Motivated by applications in risk-sensitive reinforcement learning, we study mean-variance optimization in a discounted reward Markov Decision Process (MDP). Specifically, we analyze a Temporal Difference (TD) learning algorithm with linear…

机器学习 · 计算机科学 2025-03-13 Tejaram Sangadi , L. A. Prashanth , Krishna Jagannathan

We prove the stability and global convergence of a coupled actor-critic gradient flow for infinite-horizon and entropy-regularised Markov decision processes (MDPs) in continuous state and action space with linear function approximation…

最优化与控制 · 数学 2025-10-17 Denis Zorba , David Šiška , Lukasz Szpruch

A wide variety of queueing systems can be naturally modeled as infinite-state Markov Decision Processes (MDPs). In the reinforcement learning (RL) context, a variety of algorithms have been developed to learn and optimize these MDPs. At the…

机器学习 · 计算机科学 2025-07-14 Isaac Grosof , Siva Theja Maguluri , R. Srikant
‹ 上一页 1 2 3 10 下一页 ›