Double-Loop Learning

(en.wikipedia.org)

7 points | by walterbell 20 hours ago

3 comments

  • treetalker 9 hours ago
    Similar/related, for anyone who hasn't heard of it yet: the OODA loop (https://en.m.wikipedia.org/wiki/OODA_loop)
  • VivaTechnics 19 hours ago
    Awesome!

    Technically, we could say?

    (1) Single-loop: fixes actions within fixed rules, like Reinforcement Learning.

    (2) Double-loop: questions and adapts the rules, somewhat like Meta-Reinforcement Learning.

  • 01HNNWZ0MV43FF 18 hours ago
    Five Whys is supposed to get you to this