Jul 3, 2022 • 14M

Inferring utility functions from locally non-transitive preferences. Audio version.

TL;DR: Fanboying JvN, then a nuts-and-bolts description of the von-Neumann-Morgenstern theorem. A connection to reward modeling, some simulations, and pretty figures!

 
1×
0:00
-14:07
Open in playerListen on);
    Substack App
    Download MP3
    Get a private RSS link for listening
    Subscribe to On Brains, Minds, And Their Possible Uses to get a private link for listening in your favorite podcast player. Learn about RSS.

Appears in this episode

Jan Hendrik Kirchner
Episode details
Comments

You can get notifications for audio releases on Spotify or Apple Music.

On Brains, Minds, And Their Possible Uses
Inferring utility functions from locally non-transitive preferences
Johnny did it. Last week I offhandedly mentioned the unlikely possibility that my coworkers are clones of John von Neumann. I need to explain that a bit more ——— It was a compliment, I swear! John von Neumann was... a "genius" doesn't quite do it justice. The …
Read more
a year ago · Jan Hendrik Kirchner
Share