wy Lv3
  2023-07-23 16:35:14 2023-07-23 16:35:14 Created   2023-07-23 16:41:31 2023-07-23 16:41:31 Updated  

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:
  • Author: wy
  • Created at : 2023-07-23 16:35:14
  • Updated at : 2023-07-23 16:41:31
  • Link: https://yuuee-www.github.io/blog/2023/07/23/RL/step6/RLstep6/
  • License: This work is licensed under CC BY-NC-SA 4.0.
Comments
On this page
  1. rl-Convergence and divergence