Intelligent Agent Foundations Forumsign up / log in
Intertheoretic utility comparison: examples
discussion post by Stuart Armstrong 209 days ago | discuss

A previous post introduced the theory of intertheoretic utility comparison. This post will give examples of how to do that comparison, by normalising individual utility functions.

The methods

All methods presented here obey the axioms of Relevant data, Continuity, Individual normalisation, and Symmetry. Later, we’ll see which ones follow Utility reflection, Cloning indifference, Weak irrelevance, and Strong irrelevance.

Max, min, mean

The maximum of a utility function \(u\) is \(\max_{s\in \mathbb{S}} u(s)\), while the minimum is \(\min_{s\in \mathbb{S}} u(s)\). The mean of \(u\) \(\sum_{s\in \mathbb{S}} u(s)/||\mathbb{S}||\).

  • The max-min normalisation of \([u]\) is the \(u\in [u]\) such that the maximum of \(u\) is \(1\) and the minimum is \(0\).

  • The max-mean normalisation of \([u]\) is the \(u\in [u]\) such that the maximum of \(u\) is \(1\) and the mean is \(0\).

The max-mean normalisation has an interesting feature: it’s precisely the amount of utility that an agent completely ignorant of its own utility, would pay to discover that utility (as a otherwise the agent would employ a random, ‘mean’, strategy).

For completeness, there is also:

  • The mean-min normalisation of \([u]\) is the \(u\in [u]\) such that the mean of \(u\) is \(1\) and the minimum is \(0\).

Controlling the spread

The last two methods find ways of controlling the spread of possible utilities. For any utility \(u\), define the mean difference: \(\sum_{s,s'\in\mathbb{S}} |u(s)-u(s')|\). And define the variance: \(\sum_{s\in\mathbb{S}} (u(s)-\mu)^2\), where \(\mu\) is the mean defined previously.

These lead naturally to:

  • The mean difference normalisation of \([u]\) is the \(u\in [u]\) such that \(u\) has a mean difference of \(1\).

  • The variance normalisation of \([u]\) is the \(u\in [u]\) such that \(u\) has a variance of \(1\).

Properties

The different normalisation methods obey the following axioms:

Max-min

Max-mean

Mean-min

Mean difference

Variance

Utility reflection

YES

NO

NO

YES

YES

Cloning indifference

YES

NO

NO

NO

NO

Weak Irrelevance

YES

YES

YES

NO

YES

Strong Irrelevance

YES

YES

YES

NO

NO

As can be seen, max-min normalisation, despite its crudeness, is the only one that obeys all the properties. If we have a measure on \(\mathbb{S}\), then ignoring the cloning axiom becomes more reasonable. Strong irrelevance can in fact be seen as an anti-variance; it’s because of its second order aspect that it fails this.



NEW LINKS

NEW POSTS

NEW DISCUSSION POSTS

RECENT COMMENTS

Indeed there is some kind of
by Vadim Kosoy on Catastrophe Mitigation Using DRL | 0 likes

Very nice. I wonder whether
by Vadim Kosoy on Hyperreal Brouwer | 0 likes

Freezing the reward seems
by Vadim Kosoy on Resolving human inconsistency in a simple model | 0 likes

Unfortunately, it's not just
by Vadim Kosoy on Catastrophe Mitigation Using DRL | 0 likes

>We can solve the problem in
by Wei Dai on The Happy Dance Problem | 1 like

Maybe it's just my browser,
by Gordon Worley III on Catastrophe Mitigation Using DRL | 2 likes

At present, I think the main
by Abram Demski on Looking for Recommendations RE UDT vs. bounded com... | 0 likes

In the first round I'm
by Paul Christiano on Funding opportunity for AI alignment research | 0 likes

Fine with it being shared
by Paul Christiano on Funding opportunity for AI alignment research | 0 likes

I think the point I was
by Abram Demski on Predictable Exploration | 0 likes

(also x-posted from
by Sören Mindermann on The Three Levels of Goodhart's Curse | 0 likes

(x-posted from Arbital ==>
by Sören Mindermann on The Three Levels of Goodhart's Curse | 0 likes

>If the other players can see
by Stuart Armstrong on Predictable Exploration | 0 likes

Thinking about this more, I
by Abram Demski on Predictable Exploration | 0 likes

> So I wound up with
by Abram Demski on Predictable Exploration | 0 likes

RSS

Privacy & Terms