Intrinsic Bayesian Self-Improvement on Entropic Law Spaces

Abstract

Building on a previous entropic temporal-interface complexity (ETIC) perspective, a “law” is treated as a full implementation-level stochastic mechanism: internal state dynamics, an interface to the environment, and an internal Bayesian module that runs only on its own observable history.

Keywords

• intrinsic information
• no-meta learning
• bayesian self-improvement
• entropic law spaces
• law-time complexity
• complexity
• interface entropy rate
• self-modifying systems
• posterior consistency
• exploration policies
• bandit agents
• representation learning

Identifiers and source records

• DOI
• Works entry
• ORCID