Generalized polynomial approximations in Markovian decision processes (Q1066821): Difference between revisions

From MaRDI portal
Import240304020342 (talk | contribs)
Set profile property.
ReferenceBot (talk | contribs)
Changed an Item
 
Property / cites work
 
Property / cites work: Polynomial Approximation--A New Computational Technique in Dynamic Programming: Allocation Processes / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5543516 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Splines and efficiency in dynamic programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: Multichain Markov Renewal Programs / rank
 
Normal rank
Property / cites work
 
Property / cites work: Finite state Markovian decision processes / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3206684 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Technical Note—Bounds on the Gain of a Markov Decision Process / rank
 
Normal rank
Property / cites work
 
Property / cites work: Linear Programming and Markov Decision Chains / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5335719 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Markov-Renewal Programming. I: Formulation, Finite Return Models / rank
 
Normal rank
Property / cites work
 
Property / cites work: A modified dynamic programming method for Markovian decision problems / rank
 
Normal rank
Property / cites work
 
Property / cites work: Linear programming algorithms for semi-Markovian decision processes / rank
 
Normal rank
Property / cites work
 
Property / cites work: Bounds and Transformations for Discounted Finite Markov Decision Chains / rank
 
Normal rank
Property / cites work
 
Property / cites work: Multiple Policy Improvements in Undiscounted Markov Renewal Programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: Iterative solution of the functional equations of undiscounted Markov renewal programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: The Functional Equations of Undiscounted Markov Renewal Programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: Dynamic programming, Markov chains, and the method of successive approximations / rank
 
Normal rank

Latest revision as of 18:36, 14 June 2024

scientific article
Language Label Description Also known as
English
Generalized polynomial approximations in Markovian decision processes
scientific article

    Statements

    Generalized polynomial approximations in Markovian decision processes (English)
    0 references
    0 references
    0 references
    1985
    0 references
    value function
    0 references
    Markovian decision process
    0 references
    linear superposition
    0 references
    policy iteration
    0 references
    least squares
    0 references

    Identifiers