Towards designing artificial universes for artificial agents under interaction closure

TL;DR

This paper proposes a method to design artificial universes modeled as finite Markov chains, enabling high-level processes with intrinsic explanatory power through a concept called interaction closure, facilitating the development of complex artificial agents.

Contribution

It introduces the concept of interaction closure to ensure high-level processes have explanatory power and provides a method to design universes with these properties using finite Markov chains.

Findings

Designed artificial universes exhibit high-level processes with interaction closure.

Method enables control and information transfer in artificial agent networks.

Framework supports creating complex, explanatory artificial agents.

Abstract

We are interested in designing artificial universes for artifi- cial agents. We view artificial agents as networks of high- level processes on top of of a low-level detailed-description system. We require that the high-level processes have some intrinsic explanatory power and we introduce an extension of informational closure namely interaction closure to capture this. Then we derive a method to design artificial universes in the form of finite Markov chains which exhibit high-level pro- cesses that satisfy the property of interaction closure. We also investigate control or information transfer which we see as an building block for networks representing artificial agents.