English
Related papers

Related papers: On Value Iteration Convergence in Connected MDPs

200 papers

We consider a control problem for a heterogeneous population composed of agents able to switch at any time between different options. The controller aims to maximize an average gain per time unit, supposing that the population is of…

Optimization and Control · Mathematics 2024-04-05 Quentin Jacquet , Wim van Ackooij , Clémence Alasseur , Stéphane Gaubert

This paper studies the expected value of multiplicative rewards, where rewards obtained in each step are multiplied (instead of the usual addition), in Markov chains (MCs) and Markov decision processes (MDPs). One of the key differences to…

Logic in Computer Science · Computer Science 2025-06-24 Christel Baier , Krishnendu Chatterjee , Tobias Meggendorfer , Jakob Piribauer

We present a unified framework based on primal-dual stochastic mirror descent for approximately solving infinite-horizon Markov decision processes (MDPs) given a generative model. When applied to an average-reward MDP with $A_{tot}$ total…

Machine Learning · Computer Science 2020-08-31 Yujia Jin , Aaron Sidford

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…

Machine Learning · Computer Science 2025-07-14 Isaac Grosof , Siva Theja Maguluri , R. Srikant

Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent…

Optimization and Control · Mathematics 2024-04-12 Jiacai Liu , Wenye Li , Ke Wei

In this paper we study the ergodicity properties of some adaptive Markov chain Monte Carlo algorithms (MCMC) that have been recently proposed in the literature. We prove that under a set of verifiable conditions, ergodic averages calculated…

Probability · Mathematics 2016-08-16 Christophe Andrieu , Éric Moulines

We study the problem of infinite-horizon average-reward reinforcement learning with linear Markov decision processes (MDPs). The associated Bellman operator of the problem not being a contraction makes the algorithm design challenging.…

Machine Learning · Statistics 2025-03-12 Kihyuk Hong , Woojin Chae , Yufan Zhang , Dabeen Lee , Ambuj Tewari

Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not…

Artificial Intelligence · Computer Science 2017-10-26 Dimitri Scheftelowitsch , Peter Buchholz , Vahid Hashemi , Holger Hermanns

Ye showed recently that the simplex method with Dantzig pivoting rule, as well as Howard's policy iteration algorithm, solve discounted Markov decision processes (MDPs), with a constant discount factor, in strongly polynomial time. More…

Computer Science and Game Theory · Computer Science 2010-08-04 Thomas Dueholm Hansen , Peter Bro Miltersen , Uri Zwick

Complexity of the Operations Research Theory tasks can be often diminished in cases that do not require finding the exact solution. For example, forecasting two-dimensional hierarchical time series leads us to the transportation problem…

Optimization and Control · Mathematics 2019-09-06 S. V. Rotin , I. V. Gusakov , V. Ya. Gusakov

We study the optimization of ergodic averages for multi-valued dynamical systems, i.e. where points may have multiple different forward orbits. Under upper semi-continuity assumptions, we show that the maximum space average with respect to…

Dynamical Systems · Mathematics 2025-06-03 Oliver Jenkinson , Xiaoran Li , Yuexin Liao , Yiwei Zhang

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,…

Machine Learning · Computer Science 2024-02-06 Qinbo Bai , Washim Uddin Mondal , Vaneet Aggarwal

Existing complexity bounds for point-based POMDP value iteration algorithms focus either on the curse of dimensionality or the curse of history. We derive a new bound that relies on both and uses the concept of discounted reachability; our…

Artificial Intelligence · Computer Science 2012-07-09 Trey Smith , Reid Simmons

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

We present a matrix factorization algorithm that scales to input matrices that are large in both dimensions (i.e., that contains morethan 1TB of data). The algorithm streams the matrix columns while subsampling them, resulting in low…

Optimization and Control · Mathematics 2016-12-04 Arthur Mensch , Julien Mairal , Gaël Varoquaux , Bertrand Thirion

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…

Machine Learning · Computer Science 2022-06-22 Mridul Agarwal , Qinbo Bai , Vaneet Aggarwal

The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). The temporal-difference (TD) learning is a reinforcement…

Optimization and Control · Mathematics 2020-04-29 Donghwan Lee , Jianghai Hu

Much recent research in decision theoretic planning has adopted Markov decision processes (MDPs) as the model of choice, and has attempted to make their solution more tractable by exploiting problem structure. One particular algorithm,…

Artificial Intelligence · Computer Science 2013-02-08 Craig Boutilier

We consider the multi-period portfolio optimization problem with a single asset that can be held long or short. Due to the presence of transaction costs, maximizing the immediate reward at each period may prove detrimental, as frequent…

Optimization and Control · Mathematics 2025-02-07 Chutian Ma , Paul Smith

In this short note, we give the convergence analysis of the policy in the recent famous policy mirror descent (PMD). We mainly consider the unregularized setting following [11] with generalized Bregman divergence. The difference is that we…

Optimization and Control · Mathematics 2024-06-04 Dachao Lin , Zhihua Zhang
‹ Prev 1 8 9 10 Next ›