Amorphous Fortress: Observing Emergent Behavior in Multi-Agent FSMs

TL;DR

This paper presents Amorphous Fortress, an open-ended artificial life simulation where agents as FSMs evolve through hill-climber algorithms, revealing emergent behaviors akin to complex simulation games.

Contribution

It introduces a novel spatial simulation environment with evolving FSM agents to study emergent AI behaviors in open-ended settings.

Findings

Emergent complex behaviors observed in FSM-based agents.

Evolutionary algorithms effectively generate diverse agent interactions.

The environment models behaviors similar to popular simulation games.

Abstract

We introduce a system called Amorphous Fortress -- an abstract, yet spatial, open-ended artificial life simulation. In this environment, the agents are represented as finite-state machines (FSMs) which allow for multi-agent interaction within a constrained space. These agents are created by randomly generating and evolving the FSMs; sampling from pre-defined states and transitions. This environment was designed to explore the emergent AI behaviors found implicitly in simulation games such as Dwarf Fortress or The Sims. We apply the hill-climber evolutionary search algorithm to this environment to explore the various levels of depth and interaction from the generated FSMs.