Weighted discounted Markov decision processes with perturbation (Q1806068): Difference between revisions

From MaRDI portal
Added link to MaRDI item.
ReferenceBot (talk | contribs)
Changed an Item
(One intermediate revision by one other user not shown)
Property / MaRDI profile type
 
Property / MaRDI profile type: MaRDI publication profile / rank
 
Normal rank
Property / cites work
 
Property / cites work: A Weighted Markov Decision Process / rank
 
Normal rank
Property / cites work
 
Property / cites work: Weighted reward criteria in Competitive Markov Decision Processes / rank
 
Normal rank
Property / cites work
 
Property / cites work: Markov Decision Models with Weighted Discounted Criteria / rank
 
Normal rank
Property / cites work
 
Property / cites work: Controlled Markov processes on the infinite planning horizon: Weighted and overtaking cost criteria / rank
 
Normal rank
Property / cites work
 
Property / cites work: A Note on Memoryless Rules for Controlling Sequential Control Processes / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5615108 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4739658 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5611539 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Perturbation and stability theory for Markov control problems / rank
 
Normal rank
Property / cites work
 
Property / cites work: Algorithms for singularly perturbed limiting average Markov control problems / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4863662 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3755257 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Vector-valued semi-Markovian decision programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: Optimal policies about discounted vector-valued Markovian decision programming and its algorithms / rank
 
Normal rank

Revision as of 09:52, 29 May 2024

scientific article
Language Label Description Also known as
English
Weighted discounted Markov decision processes with perturbation
scientific article

    Statements

    Weighted discounted Markov decision processes with perturbation (English)
    0 references
    0 references
    0 references
    20 February 2000
    0 references
    For the weighted reward discounted Markov decision processes with perturbation, existence of an optimal simple ultimately deterministic policy is derived and \(\delta\)-optimal policies are characterized.
    0 references
    0 references
    Markov decision processes
    0 references
    perturbation
    0 references
    optimal policies
    0 references