In algorithm 21 Spremann and Gessner [1] present a new algorithm for an ergodic Markov decision process. This note shows that this algorithm not necessarily converges and suggest a modified algorithm.In Algorithmus 21 presentieren Spremann und Gessner [1] einen neuen Algorithmus für einen ergodischen Markov-Entscheidungsprozeß. Diese Notiz zeigt, daß der Algorithmus nicht notwendigerweise konvergiert und schlägt einen modifizierten Algorithmus vor
textabstractThis paper studies two properties of the set of Markov chains induced by the determinist...
Gottinger HW. Markovian decision processes with limited state observability and unobservable costs. ...
We use nonstandard analysis to significantly generalize the well-known Markov chain ergodic theorem ...
In algorithm 21 Spremann and Gessner [1] present a new algorithm for an ergodic Markov decision proc...
In this paper we consider a completely ergodic Markov decision process with finite state and decisio...
This paper presents a policy improvement-value approximation algorithm for the average reward Markov...
In this paper we consider a completely ergodic Markov decision process with finite state and decisio...
Markov Decision Problems (MDPs) are the foundation for many problems that are of interest to researc...
Let X1, X2,… be a sequence of random variables whose finite dimensional distributions depend on a ra...
summary:In a Discounted Markov Decision Process (DMDP) with finite action sets the Value Iteration A...
International audienceWe investigate the classical active pure exploration problem in Markov Decisio...
In this paper we study a class of modified policy iteration algorithms for solving Markov decision p...
We propose a new convergence criterion for the stochastic algorithm for the optimization of probabil...
The series is devoted to the publication of monographs and high-level textbooks in mathematics, math...
It is over 30 years ago since D.J. White started his series of surveys on practical applications of ...
textabstractThis paper studies two properties of the set of Markov chains induced by the determinist...
Gottinger HW. Markovian decision processes with limited state observability and unobservable costs. ...
We use nonstandard analysis to significantly generalize the well-known Markov chain ergodic theorem ...
In algorithm 21 Spremann and Gessner [1] present a new algorithm for an ergodic Markov decision proc...
In this paper we consider a completely ergodic Markov decision process with finite state and decisio...
This paper presents a policy improvement-value approximation algorithm for the average reward Markov...
In this paper we consider a completely ergodic Markov decision process with finite state and decisio...
Markov Decision Problems (MDPs) are the foundation for many problems that are of interest to researc...
Let X1, X2,… be a sequence of random variables whose finite dimensional distributions depend on a ra...
summary:In a Discounted Markov Decision Process (DMDP) with finite action sets the Value Iteration A...
International audienceWe investigate the classical active pure exploration problem in Markov Decisio...
In this paper we study a class of modified policy iteration algorithms for solving Markov decision p...
We propose a new convergence criterion for the stochastic algorithm for the optimization of probabil...
The series is devoted to the publication of monographs and high-level textbooks in mathematics, math...
It is over 30 years ago since D.J. White started his series of surveys on practical applications of ...
textabstractThis paper studies two properties of the set of Markov chains induced by the determinist...
Gottinger HW. Markovian decision processes with limited state observability and unobservable costs. ...
We use nonstandard analysis to significantly generalize the well-known Markov chain ergodic theorem ...
DOI
Add to ORKG