Amorphous Fortress: Observing Emergent Behavior in Multi-Agent FSMs
This work addresses the challenge of understanding emergent behaviors in simulations like Dwarf Fortress for AI research, but it appears incremental as it builds on existing evolutionary methods in a new abstract environment.
The researchers tackled the problem of exploring emergent AI behaviors in open-ended artificial life simulations by introducing Amorphous Fortress, a spatial multi-agent system using finite-state machines, and they applied hill-climber evolutionary search to analyze interactions, but no concrete results or numbers were reported.
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.