Vladimir_Nesov comments on UDT agents as deontologists - Less Wrong

8 Post author: Tyrrell_McAllister 10 June 2010 05:01AM

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

Comments (109)

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

Comment author: Vladimir_Nesov 10 June 2010 12:03:31AM *  0 points [-]

But P isn't controlled by the agent's decisions.

Very very wrong. The world program P (or what it does, anyway) is the only thing that's actually controlled in this control problem statement (more generally, a list <P1, P2, P3, ...> of programs, which could equivalently be represented by one program parametrized by an integer).

Edit: I misinterpreted the way Tyrrell used "P", correction here.

Comment author: Tyrrell_McAllister 10 June 2010 12:15:00AM *  0 points [-]

Very very wrong.

Here is the relevant portion of Wei Dai's post:

These considerations lead to the following design for the decision algorithm S. S is coded with a vector <P1, P2, P3, ...> of programs that it cares about, and a utility function on vectors of the form <E1, E2, E3, …> that defines its preferences on how those programs should run. When it receives an input X, it looks inside the programs P1, P2, P3, ..., and uses its "mathematical intuition" to form a probability distribution P_Y over the set of vectors <E1, E2, E3, …> for each choice of output string Y. Finally, it outputs a string Y* that maximizes the expected utility Sum P_Y(<E1, E2, E3, …>) U(<E1, E2, E3, …>). (This specifically assumes that expected utility maximization is the right way to deal with mathematical uncertainty. Consider it a temporary placeholder until that problem is solved. Also, I'm describing the algorithm as a brute force search for simplicity. In reality, you'd probably want it to do something cleverer to find the optimal Y* more quickly.)

If I am reading him correctly, he uses the letter "P" in two different ways. In one use, he writes Pi, where i is an integer, to denote a program. In the other use, he writes P_Y, where Y is an output vector, to denote a probability distribution.

I was referring to the second use.

Comment author: Vladimir_Nesov 10 June 2010 12:35:04AM 0 points [-]

Okay, the characterization of P_Y seems right. For my reaction I blame the prior.

Returning to the original argument,

the agent always cares about all possible worlds according to how probable those worlds seemed to the agent's builders when they wrote the agent's source code.

P_Y is not a description of probabilities of possible worlds conceived by agent's builder, it's something produced by "mathematical intuition module" for a given output Y (or, strategy Y if you incorporate the later patch to UDT).

Comment author: Tyrrell_McAllister 10 June 2010 12:44:58AM 0 points [-]

P_Y is not a description of probabilities of possible worlds conceived by agent's builder, it's something produced by "mathematical intuition module" for a given output Y (or, strategy Y if you incorporate the later patch to UDT).

You are right here. Like you, I misremembered Wei Dai's notation. See my last (I hope) edit to that comment.

I would appreciate it if you edited your comment where you say that I was "very very wrong" to say that P isn't controlled by the agent's decisions.

Comment author: Vladimir_Nesov 10 June 2010 12:50:17AM *  3 points [-]

It's easier to have a linear discussion, rather than trying to patch everything by reediting it from the start (just saying, you are doing this for the third time to that poor top-level comment). You've got something wrong, then I've got something wrong, the errors were corrected as the discussion developed, moving on. The history doesn't need to be corrected. (I insert corrections to comments this way, without breaking the sequence.)

Comment author: Tyrrell_McAllister 10 June 2010 12:52:58AM 0 points [-]

Thank you for the edit.