Maximal Algorithmic Caliber and Algorithmic Causal Network Inference: General Principles of Real-World General Intelligence?

TL;DR

This paper introduces the Principle of Maximum Algorithmic Caliber, linking thermodynamics and computational processes, suggesting that intelligent systems operate by modeling environments with algorithmic Markov networks to achieve optimality.

Contribution

It extends thermodynamic principles to stochastic computational processes and proposes a new principle guiding the hypothesizing of computational processes in intelligent systems.

Findings

Algorithmic Markov conditions lead to maximized algorithmic caliber.

Real-world cognitive systems may model environments using algorithmic Markov networks.

Proposes a theoretical framework for general intelligence based on thermodynamics and computation.

Abstract

Ideas and formalisms from far-from-equilibrium thermodynamics are ported to the context of stochastic computational processes, via following and extending Tadaki's algorithmic thermodynamics. A Principle of Maximum Algorithmic Caliber is proposed, providing guidance as to what computational processes one should hypothesize if one is provided constraints to work within. It is conjectured that, under suitable assumptions, computational processes obeying algorithmic Markov conditions will maximize algorithmic caliber. It is proposed that in accordance with this, real-world cognitive systems may operate in substantial part by modeling their environments and choosing their actions to be (approximate and compactly represented) algorithmic Markov networks. These ideas are suggested as potential early steps toward a general theory of the operation of pragmatic generally intelligent systems.