Measuring Intelligence and Growth Rate: Variations on Hibbard's Intelligence Measure
This work addresses the problem of defining and measuring intelligence for adversarial sequence predictors, with potential indirect applications to Artificial General Intelligence (AGI), but it is incremental as it builds on and refines existing ideas.
The paper separates Hibbard's intelligence measure into two components: measuring intelligence based on runtime growth rates of defeated competitors and specific methods for measuring those growth rates. It proposes novel intelligence taxonomies using Big-O and Big-Theta notation, challenging conventional intelligence measurement concepts.
In 2011, Hibbard suggested an intelligence measure for agents who compete in an adversarial sequence prediction game. We argue that Hibbard's idea should actually be considered as two separate ideas: first, that the intelligence of such agents can be measured based on the growth rates of the runtimes of the competitors that they defeat; and second, one specific (somewhat arbitrary) method for measuring said growth rates. Whereas Hibbard's intelligence measure is based on the latter growth-rate-measuring method, we survey other methods for measuring function growth rates, and exhibit the resulting Hibbard-like intelligence measures and taxonomies. Of particular interest, we obtain intelligence taxonomies based on Big-O and Big-Theta notation systems, which taxonomies are novel in that they challenge conventional notions of what an intelligence measure should look like. We discuss how intelligence measurement of sequence predictors can indirectly serve as intelligence measurement for agents with Artificial General Intelligence (AGIs).