rl-Convergence and divergence

wy Lv3

rl-Convergence and divergence

Convergence Questions

Convergence of MC

Convergence of TD

Theorem:

TD is not a gradient

Example of divergence

use TD only on this transition

Residual Bellman updates

  • Title: rl-Convergence and divergence
  • Author: wy
  • Created at : 2023-07-23 08:35:14
  • Updated at : 2023-07-23 08:41:31
  • Link: https://yue-ruby-w.site/2023/07/23/2023-07-23-RL-step6-RLstep6/
  • License: This work is licensed under CC BY-NC-SA 4.0.
On this page
rl-Convergence and divergence