Approximations for constrained Markov decision problems

Name: Approximations for constrained Markov decision problems
Author: Saldı, Naci, Linder, T., Yüksel, S.

İsim	Approximations for constrained Markov decision problems
Yazar	Saldı, Naci, Linder, T., Yüksel, S.
Basım Tarihi:	2018
Basım Yeri	- Springer
Tür	Kitap
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-3-319-79032-9
Kayıt Numarası	cd2bc5f0-8452-4100-ac56-ec7b27500608
Lokasyon	Natural and Mathematical Sciences
Tarih	2018
Örnek Metin	This chapter studies the finite-state approximation of a discrete-time constrained Markov decision process with compact state space, under the discounted and average cost criteria. Using the linear programming formulation of the constrained discounted problem, we prove the convergence of the optimal value function of the finite-state model to the optimal value function of the original model. Under further continuity conditions on the transition probability of the original discounted model, we also establish a method to compute approximately optimal policies. For the average cost criterion, instead of using the finite-state linear programming approximation method, we use a direct method to establish analogous results under drift and minorization conditions which guarantee the geometric ergodicity of Markov chains induced by stationary policies.
DOI	10.1007/978-3-319-79033-6_6

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Approximations for constrained Markov decision problems

Yazar Saldı, Naci, Linder, T., Yüksel, S.

Basım Tarihi 2018

Basım Yeri - Springer

Tür Kitap

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-3-319-79032-9

Kayıt Numarası cd2bc5f0-8452-4100-ac56-ec7b27500608

Lokasyon Natural and Mathematical Sciences

Tarih 2018

Örnek Metin This chapter studies the finite-state approximation of a discrete-time constrained Markov decision process with compact state space, under the discounted and average cost criteria. Using the linear programming formulation of the constrained discounted problem, we prove the convergence of the optimal value function of the finite-state model to the optimal value function of the original model. Under further continuity conditions on the transition probability of the original discounted model, we also establish a method to compute approximately optimal policies. For the average cost criterion, instead of using the finite-state linear programming approximation method, we use a direct method to establish analogous results under drift and minorization conditions which guarantee the geometric ergodicity of Markov chains induced by stationary policies.

DOI 10.1007/978-3-319-79033-6_6