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

2026-04-13

AI Summary

This work addresses the tendency of existing differentiable multi-agent systems, such as PD-NCA, to converge to frozen equilibria or unstructured noise when attempting to generate open-ended complexity. To overcome this limitation, the paper introduces PBT-NCA—a meta-evolutionary framework that integrates population-based training (PBT), behavioral representations, and diversity rewards. For the first time, it incorporates both historical behavioral novelty and current visual diversity as composite evolutionary objectives in neural cellular automata training. This approach drives populations to continually evolve lifelike strategies—including periodic waves, spore dispersal, and migratory macrostructures—sustaining effective complexity at the “edge of chaos” over extended timescales. The method significantly mitigates mode collapse observed in conventional approaches, achieving dynamically rich and diverse open-ended evolution.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Machine Learning: Evolutionary Learning
• Search and Optimization: Evolutionary Computation

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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".

Problem

• open-endedness
• artificial life
• Neural Cellular Automata
• complexity
• self-organization

Innovation

• open-endedness
• population-based training
• neural cellular automata
• behavioral novelty
• edge of chaos