Intelligence via ultrafilters: structural properties of some intelligence comparators of deterministic Legg-Hutter agents
This provides a theoretical framework for intelligence comparison in reinforcement learning, but it is incremental as it builds on existing Legg-Hutter agent models and leaves practical applicability open.
The paper tackles the problem of comparing the relative intelligence of two deterministic Legg-Hutter agents by proposing a comparator based on viewing agents as candidates in an election where environments vote via rewards, and proves structural theorems about these comparators.
Legg and Hutter, as well as subsequent authors, considered intelligent agents through the lens of interaction with reward-giving environments, attempting to assign numeric intelligence measures to such agents, with the guiding principle that a more intelligent agent should gain higher rewards from environments in some aggregate sense. In this paper, we consider a related question: rather than measure numeric intelligence of one Legg- Hutter agent, how can we compare the relative intelligence of two Legg-Hutter agents? We propose an elegant answer based on the following insight: we can view Legg-Hutter agents as candidates in an election, whose voters are environments, letting each environment vote (via its rewards) which agent (if either) is more intelligent. This leads to an abstract family of comparators simple enough that we can prove some structural theorems about them. It is an open question whether these structural theorems apply to more practical intelligence measures.