Skip navigation
Skip navigation

Browsing by Author Greensmith, Evan

Or enter first few letters:  
Showing results 1 to 3 of 3
01front.pdf.jpg

Policy Gradient Methods: Variance Reduction and Stochastic Convergence

Author(s)Greensmith, Evan
TypeThesis (PhD)
Date Published2005
Date Created-

Variance reduction techniques for gradient estimates in reinforcement learning

Author(s)Greensmith, Evan; Bartlett, Peter; Baxter, Jon
TypeConference paper
Date Published2002
Date CreatedSeptember 2 2002

Variance reduction techniques for gradient estimates in reinforcement learning

Author(s)Greensmith, Evan; Bartlett, Peter L; Baxter, Jonathan
TypeJournal article
Date Published2004
Date Created-
  • previous
  • 1
  • next

Updated:  12 April 2016/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator