Block-successive approximation for a discounted Markov decision model (Q2265958): Difference between revisions
From MaRDI portal
Set profile property. |
ReferenceBot (talk | contribs) Changed an Item |
||
(One intermediate revision by one other user not shown) | |||
Property / full work available at URL | |||
Property / full work available at URL: https://doi.org/10.1016/0304-4149(85)90046-8 / rank | |||
Normal rank | |||
Property / OpenAlex ID | |||
Property / OpenAlex ID: W2080054160 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Contraction Mappings in the Theory Underlying Dynamic Programming / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4427313 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Some Bounds for Discounted Sequential Decision Processes / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4173220 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q5342712 / rank | |||
Normal rank |
Latest revision as of 17:12, 14 June 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Block-successive approximation for a discounted Markov decision model |
scientific article |
Statements
Block-successive approximation for a discounted Markov decision model (English)
0 references
1985
0 references
We suggest a new successive approximation method to compute the optimal discounted reward for finite state and action, discrete time, discounted Markov decision chains. The method is based on a block partitioning of the (stochastic) matrices corresponding to the stationary policies. The method is particularly attractive when the transition matrices are jointly nearly decomposable or nearly completely decomposable.
0 references
successive approximation
0 references
optimal discounted reward
0 references
finite state and action, discrete time, discounted Markov decision chains
0 references
block partitioning
0 references
stationary policies
0 references