jessicat comments on FAI Research Constraints and AGI Side Effects - LessWrong

14 Post author: JustinShovelain 03 June 2015 07:25PM

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

Comments (58)

Sort By: Best

You are viewing a single comment's thread. Show more comments above.

Comment author: jessicat 13 June 2015 07:00:04AM 0 points [-]

It's not a specific programming language, I guess it's meant to look like Church. It could be written as:

(query
. (define a (p))
. (foreach (range n) (lambda i)
. . (define x (x-prior))
. . (factor (log (U x a)))))

Well so does the sigmoided version

It samples an action proportional to p(a) E[sigmoid(U) | a]. This can't be written as a function of E[U | a].