Manfred comments on Towards a New Decision Theory for Parallel Agents - Less Wrong

4 Post author: potato 07 August 2011 11:39PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (15)

You are viewing a single comment's thread.

Comment author: Manfred 08 August 2011 10:06:24PM 1 point [-]

The sum of utility functions is also a utility function. Since humans can be inconsistent, our modules don't interact independently, but rather can amplify other parts and similar messy stuff. Once you allow that whole range of interactions, you're screwed - there's already no solution to many multiplayer games when things are independent!