Target Network and Truncation Overcome the Deadly Triad in \(\boldsymbol{Q}\)-Learning (Q6148353)

From MaRDI portal
scientific article; zbMATH DE number 7786787
Language Label Description Also known as
English
Target Network and Truncation Overcome the Deadly Triad in \(\boldsymbol{Q}\)-Learning
scientific article; zbMATH DE number 7786787

    Statements

    Target Network and Truncation Overcome the Deadly Triad in \(\boldsymbol{Q}\)-Learning (English)
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    11 January 2024
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    reinforcement learning
    0 references
    \(Q\)-learning
    0 references
    linear function approximation
    0 references
    finite-sample analysis
    0 references
    0 references