What use is utility?
If we must use the expected utility maximizer model for humans, what is the utility we should use?
2025-06-05 — 2026-04-09
Wherein the implied utility functions of animals are considered in light of machine-learning optimisation, and value learning is introduced as a framework for inferring preferences from behaviour.
Because machine learning models so often optimise a loss function, there is a degree to which we must internalise a world in which agents have something like a fixed utility which they pursue, because at least some agents do something like that.
If we need to construct such a pretence for animals, what does the implied utility function look like?
cf ecology of mind, what are human values.
And note of course, that many ML algorithms don’t need utilities, but might subsist on intrinsic motivation.
1 Value learning
One answer comes from reinforcement learning.. See value learning.