Can rationality be measured?
This addresses a foundational problem in AI and decision theory, but it appears incremental as it builds on existing optimization concepts.
This paper tackles the problem of whether rationality can be computed by defining it based on information completeness, brain perfection, and optimization, and concludes that rationality can be computed for convex optimization problems.
This paper studies whether rationality can be computed. Rationality is defined as the use of complete information, which is processed with a perfect biological or physical brain, in an optimized fashion. To compute rationality one needs to quantify how complete is the information, how perfect is the physical or biological brain and how optimized is the entire decision making system. The rationality of a model (i.e. physical or biological brain) is measured by the expected accuracy of the model. The rationality of the optimization procedure is measured as the ratio of the achieved objective (i.e. utility) to the global objective. The overall rationality of a decision is measured as the product of the rationality of the model and the rationality of the optimization procedure. The conclusion reached is that rationality can be computed for convex optimization problems.