Ultimate Intelligence Part II: Physical Measure and Complexity of Intelligence

We investigate physical measures and limits of intelligence that are objective and useful. We propose a universal measure of operator induction fitness, and show how it can be used in a reinforcement learning model, and a self-preserving agent model based on the free energy principle. We extend logical depth and conceptual jump size measures to stochastic domains, and elucidate their relations. We introduce a graphical model of computational complexity, apply physical complexity measures that involve space-time extents, energy, and space to universal induction, and introduce new variants of conceptual jump size. We show relations between energy, logical depth and volume of computation for inductive inference. We also introduce an energy-bounded algorithmic complexity measure. 1