Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training

TL;DR

This paper introduces PBT-NCA, a meta-evolutionary algorithm that evolves Petri Dish Neural Cellular Automata to spontaneously generate diverse, lifelike phenomena and sustain open-ended complexity through continuous evolutionary pressure.

Contribution

It presents a novel evolutionary method that promotes emergent lifelike behaviors and complexity in multi-agent cellular automata, advancing open-ended artificial life research.

Findings

PBT-NCA generates diverse emergent phenomena like waves and scattering.

The system maintains a balance between order and chaos, fostering complexity.

It autonomously discovers survival and self-organization strategies.

Abstract

The generation of sustained, open-ended complexity from local interactions remains a fundamental challenge in artificial life. Differentiable multi-agent systems, such as Petri Dish Neural Cellular Automata (PD-NCA), exhibit rich self-organization driven purely by spatial competition; however, they are highly sensitive to hyperparameters and frequently collapse into uninteresting patterns and dynamics, such as frozen equilibria or structureless noise. In this paper, we introduce PBT-NCA, a meta-evolutionary algorithm that evolves a population of PD-NCAs subject to a composite objective that rewards both historical behavioral novelty and contemporary visual diversity. Driven by this continuous evolutionary pressure, PBT-NCA spontaneously generates a plethora of emergent lifelike phenomena over extended horizons-a hallmark of true open-endedness. Strikingly, the substrate autonomously discovers diverse morphological survival and self-organization strategies. We observe highly regular, coordinated periodic waves; spore-like scattering where homogeneous groups eject cell-like clusters to colonize distant territories; and fluid, shape-shifting macro-structures that migrate across the substrate, maintaining stable outer boundaries that enclose highly active interiors. By actively penalizing monocultures and dead states, PBT-NCA sustains a state of effective complexity that is neither globally ordered nor globally random, operating persistently at the "edge of chaos".