English
Related papers

Related papers: Linking PageRank, Time Reversal, and Policy Evalua…

200 papers

What are the functionals of the reward that can be computed and optimized exactly in Markov Decision Processes?In the finite-horizon, undiscounted setting, Dynamic Programming (DP) can only handle these operations efficiently for certain…

Artificial Intelligence · Computer Science 2024-02-20 Alexandre Marthe , Aurélien Garivier , Claire Vernade

We revisit the estimation bias in policy gradients for the discounted episodic Markov decision process (MDP) from Deep Reinforcement Learning (DRL) perspective. The objective is formulated theoretically as the expected returns discounted…

Machine Learning · Computer Science 2023-02-13 Haoxuan Pan , Deheng Ye , Xiaoming Duan , Qiang Fu , Wei Yang , Jianping He , Mingfei Sun

A Markov decision problem is called reversible if the stationary controlled Markov chain is reversible under every stationary Markovian strategy. A natural application in which such problems arise is in the control of Metropolis-Hastings…

Probability · Mathematics 2022-07-13 Venkat Anantharam

This note describes sufficient conditions under which total-cost and average-cost Markov decision processes (MDPs) with general state and action spaces, and with weakly continuous transition probabilities, can be reduced to discounted MDPs.…

Optimization and Control · Mathematics 2017-11-21 Eugene A. Feinberg , Jefferson Huang

We present a method for a certain class of Markov Decision Processes (MDPs) that can relate the optimal policy back to one or more reward sources in the environment. For a given initial state, without fully computing the value function,…

Machine Learning · Computer Science 2018-06-12 Josh Bertram , Peng Wei

This paper studies discounted Markov Decision Processes (MDPs) with finite sets of states and actions. Value iteration is one of the major methods for finding optimal policies. For each discount factor, starting from a finite number of…

Optimization and Control · Mathematics 2025-07-15 Eugene A. Feinberg , Gaojin He

We characterize the reachability probabilities in stochastic directed graphs by means of reinforcement learning methods. In particular, we show that the dynamics of the transition probabilities in a stochastic digraph can be modeled via a…

Artificial Intelligence · Computer Science 2022-02-28 Corrado Possieri , Mattia Frasca , Alessandro Rizzo

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 study the general approach to accelerating the convergence of the most widely used solution method of Markov decision processes with the total expected discounted reward. Inspired by the monotone behavior of the contraction mappings in…

Optimization and Control · Mathematics 2008-03-28 Oleksandr Shlakhter , Chi-Guhn Lee , Dmitry Khmelev , Nasser Jaber

This paper presents a numerical method to calculate the value function for a general discounted impulse control problem for piecewise deterministic Markov processes. Our approach is based on a quantization technique for the underlying…

Probability · Mathematics 2011-08-31 Benoîte de Saporta , François Dufour

Motivated by applications in telecommunications, computer scienceand physics, we consider a discrete-time Markov process withrestart. At each step the process eitherwith a positive probability restarts from a given distribution, orwith the…

Performance · Computer Science 2017-03-13 Konstantin Avrachenkov , Alexey Piunovskiy , Yi Zhang

In this work, we consider a cooperative multi-agent Markov decision process (MDP) involving m agents. At each decision epoch, all the m agents independently select actions in order to maximize a common long-term objective. In the policy…

Machine Learning · Computer Science 2024-05-01 Lakshmi Mandal , Chandrashekar Lakshminarayanan , Shalabh Bhatnagar

We study fixed-policy evaluation for finite Markov chains that may be reducible and periodic. Classical evaluation methods with gain and bias decomposition are not always diagnostic: the gain records only invariant Ces\`aro averages, while…

Machine Learning · Statistics 2026-05-11 Yang Xu , Vaneet Aggarwal

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

We study the policy evaluation problem in multi-agent reinforcement learning. In this problem, a group of agents works cooperatively to evaluate the value function for the global discounted accumulative reward problem, which is composed of…

Optimization and Control · Mathematics 2019-06-04 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg

The goal of reinforcement learning is estimating a policy that maps states to actions and maximizes the cumulative reward of a Markov Decision Process (MDP). This is oftentimes achieved by estimating first the optimal (reward) value…

Machine Learning · Computer Science 2024-05-29 Sergio Rozada , Antonio G. Marques

We present algorithms to effectively represent a set of Markov decision processes (MDPs), whose optimal policies have already been learned, by a smaller source subset for lifelong, policy-reuse-based transfer learning in reinforcement…

Artificial Intelligence · Computer Science 2016-05-03 M. M. Hassan Mahmud , Majd Hawasly , Benjamin Rosman , Subramanian Ramamoorthy

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

In this paper, we equip the conventional discrete-time queueing network with a Markovian input process, that, in addition to the usual short-term stochastics, governs the mid- to long-term behavior of the links between the network nodes.…

Systems and Control · Electrical Eng. & Systems 2020-04-07 Richard Schoeffauer , Gerhard Wunder

We study the problem of learning Markov decision processes with finite state and action spaces when the transition probability distributions and loss functions are chosen adversarially and are allowed to change with time. We introduce an…

Machine Learning · Computer Science 2013-03-14 Yasin Abbasi-Yadkori , Peter L. Bartlett , Csaba Szepesvari