🛠️ Steven Gong

Search

SearchSearch

Jul 17, 2025, 1 min read

Bellman Error

L(ϕ,D)=(s,a,r,s′,d)∼DE​​(Qϕ​(s,a)−(r+γ(1−d)maxa′​Qϕ​(s′,a′)))2​

  • https://spinningup.openai.com/en/latest/algorithms/ddpg.html

Graph View

Backlinks

  • No backlinks found

Created with Quartz, © 2025

  • Blog
  • LinkedIn
  • Twitter
  • GitHub