Ultimate Intelligence Part I: Physical Completeness and Objectivity of Induction
This work addresses foundational issues in universal induction for AI and physics, though it appears incremental as it builds on existing Solomonoff induction theory.
The paper argues that Solomonoff induction is physically complete and applicable to quantum mechanics, proposing an objective reference machine based on physical message complexity to address objections to universal induction.
We propose that Solomonoff induction is complete in the physical sense via several strong physical arguments. We also argue that Solomonoff induction is fully applicable to quantum mechanics. We show how to choose an objective reference machine for universal induction by defining a physical message complexity and physical message probability, and argue that this choice dissolves some well-known objections to universal induction. We also introduce many more variants of physical message complexity based on energy and action, and discuss the ramifications of our proposals.