Sarah Marzen
  • Main
  • People
  • Contact
  • Google Scholar
  • Random ruminations
  • Selected Publications
  • Main
  • People
  • Contact
  • Google Scholar
  • Random ruminations
  • Selected Publications

Random musings

Some of these information-theoretic objective functions drive us in circles

5/12/2020

0 Comments

 
I've been wanting to write this post for a while, but never had the courage.  But here goes.

Every so often, I encounter a paper that proposes a new objective function for agent behavior.  Sometimes, something like predictive information is proposed; sometimes, something more like entropy rate is proposed.  In both cases, I have a bit of an issue.

When we try and say maximize predictability while minimizing memory, you end up either flipping coins (when you penalize memory too much) or running in very large circles (when you don't penalize memory enough).  There doesn't usually seem to be an interesting intermediate behavior.

When you maximize entropy rate, you typically end up flipping coins.

The key to making these objective functions interesting, I think, is to add enough constraints that they start doing interesting things.  And since this now impinges upon an old project that I may pick up again in the near future, that's all I'll say!
0 Comments



Leave a Reply.

    Author

    Write something about yourself. No need to be fancy, just an overview.

    Archives

    November 2022
    July 2022
    December 2021
    November 2021
    March 2021
    February 2021
    May 2020
    July 2019
    May 2017

    Categories

    All

    RSS Feed

Proudly powered by Weebly