English
Related papers

Related papers: Stochastic first-order methods for average-reward …

200 papers

In this paper, we propose a policy gradient method for confounded partially observable Markov decision processes (POMDPs) with continuous state and observation spaces in the offline setting. We first establish a novel identification result…

Machine Learning · Statistics 2023-12-04 Mao Hong , Zhengling Qi , Yanxun Xu

Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which…

Artificial Intelligence · Computer Science 2020-02-28 Tomas Brazdil , Krishnendu Chatterjee , Petr Novotny , Jiri Vahala

A popular approach to solving a decision process with non-Markovian rewards (NMRDP) is to exploit a compact representation of the reward function to automatically translate the NMRDP into an equivalent Markov decision process (MDP) amenable…

Artificial Intelligence · Computer Science 2013-01-07 Sylvie Thiebaux , Froduald Kabanza , John Slanley

This paper studies Markov Decision Processes (MDPs) with atomless initial state distributions and atomless transition probabilities. Such MDPs are called atomless. The initial state distribution is considered to be fixed. We show that for…

Optimization and Control · Mathematics 2018-10-26 Eugene A. Feinberg , Aleksey B. Piunovskiy

We consider discounted infinite-horizon constrained Markov decision processes (CMDPs), where the goal is to find an optimal policy that maximizes the expected cumulative reward while satisfying expected cumulative constraints. Motivated by…

Machine Learning · Computer Science 2025-03-04 Tingting Ni , Maryam Kamgarpour

In many operations management problems, we need to make decisions sequentially to minimize the cost while satisfying certain constraints. One modeling approach to study such problems is constrained Markov decision process (CMDP). When…

Optimization and Control · Mathematics 2021-01-27 Yi Chen , Jing Dong , Zhaoran Wang

We study reinforcement learning for continuous-time Markov decision processes (MDPs) in the finite-horizon episodic setting. In contrast to discrete-time MDPs, the inter-transition times of a continuous-time MDP are exponentially…

Machine Learning · Computer Science 2023-10-04 Xuefeng Gao , Xun Yu Zhou

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…

Optimization and Control · Mathematics 2025-10-16 Dongsheng Ding , Kaiqing Zhang , Jiali Duan , Tamer Başar , Mihailo R. Jovanović

A tenet of reinforcement learning is that the agent always observes rewards. However, this is not true in many realistic settings, e.g., a human observer may not always be available to provide rewards, sensors may be limited or…

Machine Learning · Computer Science 2026-03-24 Alireza Kazemipour , Simone Parisi , Matthew E. Taylor , Michael Bowling

Markov decision processes (MDP) are a well-established model for sequential decision-making in the presence of probabilities. In robust MDP (RMDP), every action is associated with an uncertainty set of probability distributions, modelling…

Artificial Intelligence · Computer Science 2024-12-16 Tobias Meggendorfer , Maximilian Weininger , Patrick Wienhöft

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Machine Learning · Computer Science 2020-08-26 Lingwei Zhu , Takamitsu Matsubara

In this paper, we consider a class of continuous-time, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation methods and sampling-based algorithms for deterministic path planning,…

Robotics · Computer Science 2012-02-27 Vu Anh Huynh , Sertac Karaman , Emilio Frazzoli

In this paper, we give a new approximate dynamic programming (ADP) method to solve large-scale Markov decision programming (MDP) problem. In comparison with many classic ADP methods which have large number of constraints, we formulate an…

Optimization and Control · Mathematics 2025-07-15 Di Zhang

To overcome the curse of dimensionality and curse of modeling in Dynamic Programming (DP) methods for solving classical Markov Decision Process (MDP) problems, Reinforcement Learning (RL) algorithms are popular. In this paper, we consider…

Machine Learning · Computer Science 2018-11-29 Arghyadip Roy , Vivek Borkar , Abhay Karandikar , Prasanna Chaporkar

Markov Decision Processes (MDPs) are a mathematical framework for modeling sequential decision making under uncertainty. The classical approaches for solving MDPs are well known and have been widely studied, some of which rely on…

Machine Learning · Computer Science 2018-05-18 Joshua R. Bertram , Xuxi Yang , Peng Wei

We study infinite-horizon Constrained Markov Decision Processes (CMDPs) with general policy parameterizations and multi-layer neural network critics. Existing theoretical analyses for constrained reinforcement learning largely rely on…

Machine Learning · Computer Science 2026-03-10 Anirudh Satheesh , Pankaj Kumar Barman , 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…

Machine Learning · Computer Science 2026-02-10 Anirudh Satheesh , Vaneet Aggarwal

Dynamic optimization of mean and variance in Markov decision processes (MDPs) is a long-standing challenge caused by the failure of dynamic programming. In this paper, we propose a new approach to find the globally optimal policy for…

Optimization and Control · Mathematics 2023-02-28 Li Xia , Shuai Ma

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

This paper analyzes reinforcement learning (RL) algorithms for Markov decision processes (MDPs) under the average-reward criterion. We focus on Q-learning algorithms based on relative value iteration (RVI), which are model-free stochastic…

Machine Learning · Computer Science 2024-08-30 Yi Wan , Huizhen Yu , Richard S. Sutton