Exploring Flow-Lenia Universes with a Curiosity-driven AI Scientist: Discovering Diverse Ecosystem Dynamics

TL;DR

This paper introduces a curiosity-driven AI method to automatically discover and analyze diverse ecosystem dynamics in Flow-Lenia cellular automata, revealing complex self-organizing behaviors beyond previous approaches.

Contribution

The paper extends diversity search algorithms with curiosity-driven exploration in Flow-Lenia, enabling discovery of complex collective behaviors and ecosystem dynamics in large environments.

Findings

More diverse dynamics found compared to random search

Ecosystemic simulations reveal complex collective behaviors

Interactive tool supports human-AI collaborative exploration

Abstract

We present a method for the automated discovery of system-level dynamics in Flow-Lenia--a continuous cellular automaton (CA) with mass conservation and parameter localization-using a curiosity--driven AI scientist. This method aims to uncover processes leading to self-organization of evolutionary and ecosystemic dynamics in CAs. We build on previous work which uses diversity search algorithms in Lenia to find self-organized individual patterns, and extend it to large environments that support distinct interacting patterns. We adapt Intrinsically Motivated Goal Exploration Processes (IMGEPs) to drive exploration of diverse Flow-Lenia environments using simulation-wide metrics, such as evolutionary activity, compression-based complexity, and multi-scale entropy. We test our method in two experiments, showcasing its ability to illuminate significantly more diverse dynamics compared to random search. We show qualitative results illustrating how ecosystemic simulations enable self-organization of complex collective behaviors not captured by previous individual pattern search and analysis. We complement automated discovery with an interactive exploration tool, creating an effective human-AI collaborative workflow for scientific investigation. Though demonstrated specifically with Flow-Lenia, this methodology provides a framework potentially applicable to other parameterizable complex systems where understanding emergent collective properties is of interest.