Deprecated: $wgMWOAuthSharedUserIDs=false is deprecated, set $wgMWOAuthSharedUserIDs=true, $wgMWOAuthSharedUserSource='local' instead [Called from MediaWiki\HookContainer\HookContainer::run in /var/www/html/w/includes/HookContainer/HookContainer.php at line 135] in /var/www/html/w/includes/Debug/MWDebug.php on line 372
Approximate Newton Policy Gradient Algorithms - MaRDI portal

Approximate Newton Policy Gradient Algorithms (Q6074547)

From MaRDI portal
scientific article; zbMATH DE number 7749379
Language Label Description Also known as
English
Approximate Newton Policy Gradient Algorithms
scientific article; zbMATH DE number 7749379

    Statements

    title
    Approximate Newton Policy Gradient Algorithms (English)
    0 references
    author
    Haoya Li
    0 references
    Samarth Gupta
    0 references
    Q6074546
    0 references
    Lexing Ying
    0 references
    Inderjit S. Dhillon
    0 references
    publication date
    12 October 2023
    0 references
    zbMATH Keywords
    policy gradient algorithm
    0 references
    approximate Newton method
    0 references
    quadratic convergence
    0 references
    Markov decision process
    0 references
    entropy regularization
    0 references
    reinforcement learning
    0 references

    Identifiers

    arXiv ID
    2110.02398
    0 references
    DOI
    10.1137/22m1492088
    0 references
    Mathematics Subject Classification ID
    90C40
    0 references
    65K10
    0 references
    49M15
    0 references
    90C06
    0 references
    90C53
    0 references
    68T07
    0 references
    zbMATH DE Number
    7749379
    0 references
     
    Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=Item:Q6074547&oldid=37566943"
    Powered by MediaWiki