Why does being updateless require thinking through all possibilities in advance? Can you not make a general commitment to follow UDT, but wait until you actually face the decision problem to figure out which specific action UDT recommends taking?

Sure, but what computation do you then do, to figure out what UDT recommends? You have to have, written down, a specific prior which you evaluate everything with. That's the problem. As discussed in Embedded World Models, a Bayesian prior is not a very good object for an embedded agent's beliefs, due to realizability/grain-of-truth concerns; that is, specifically because a Bayesian prior needs to list all possibilities explicitly (to a greater degree than, e.g., logical induction).

Decision Theory

by abramdemski, Scott Garrabrant 1 min read31st Oct 201837 comments


Ω 24

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.

(A longer text-based version of this post is also available on MIRI's blog here, and the bibliography for the whole sequence can be found here.)

The next post in this sequence, 'Embedded Agency', will come out on Friday, November 2nd.

Tomorrow’s AI Alignment Forum sequences post will be 'What is Ambitious Value Learning?' in the sequence 'Value Learning'.