Back to LessWrong

Difference between revisions of "5-and-10"

From Lesswrongwiki

Jump to: navigation, search
m (turn literal into blockquote)
(two verssions)
Line 1: Line 1:
The five-and-ten problem (sometimes known as the heavy ghost problem) is a problem in certain types of UDT-like decision theories, when the fact that a counterfactual is known to be false makes the algorithm implement it.
+
[http://lesswrong.com/lw/91c/so_you_want_to_save_the_world/5jdp One version of the 5-and-10 problem] is "I have to decide between $5 and $10. Suppose I decide to choose $5. I know that I'm a money-optimizer, so if I do this, $5 must be more money than $10, so this alternative is better. Therefore, I should choose $5."
 +
 
 +
Another version, sometimes known as the heavy ghost problem, is a problem in certain types of UDT-like decision theories, when the fact that a counterfactual is known to be false makes the algorithm implement it.
  
 
Specifically, let there be a decision problem which involves the choice between $5 and $10, a utility function that values the $10 more than the $5, and an algorithm A that reasons something like:
 
Specifically, let there be a decision problem which involves the choice between $5 and $10, a utility function that values the $10 more than the $5, and an algorithm A that reasons something like:

Revision as of 22:34, 8 March 2016

One version of the 5-and-10 problem is "I have to decide between $5 and $10. Suppose I decide to choose $5. I know that I'm a money-optimizer, so if I do this, $5 must be more money than $10, so this alternative is better. Therefore, I should choose $5."

Another version, sometimes known as the heavy ghost problem, is a problem in certain types of UDT-like decision theories, when the fact that a counterfactual is known to be false makes the algorithm implement it.

Specifically, let there be a decision problem which involves the choice between $5 and $10, a utility function that values the $10 more than the $5, and an algorithm A that reasons something like:

"Look at all proposition of the type '(A decides to do X) implies (Utility=y)', and find the X that maximises y, then do X."

When faced with the above problem, certain types of algorithm can reason:

"The utility of $10 is greater than the utility of $5. Therefore I will never decide to choose $5. Therefore (A decides to do 'choose $5') is a false statement. Since a false statement implies anything, (A decides to do 'choose $5') implies (Utility=y) for any, arbitrarily high, value of y. Therefore this is the utility maximising decision, and I should choose $5."

That is the informal, natural language statement of the problem. Whether the algorithm is actually vulnerable to the 5-and-10 problem depends on the details of what the algorithm is allowed to deduce about itself.