Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis (Q5162625)

From MaRDI portal
scientific article; zbMATH DE number 7419556
Language Label Description Also known as
English
Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
scientific article; zbMATH DE number 7419556

    Statements

    Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis (English)
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    3 November 2021
    0 references
    0 references
    0 references
    0 references
    0 references
    temporal difference learning
    0 references
    Polyak-Ruppert averaging
    0 references
    variance reduction
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references