Seeking Open-Ended Evolution in Swarm Chemistry II: Analyzing Long-Term Dynamics via Automated Object Harvesting
This work addresses the problem of understanding open-ended evolution in artificial life systems for researchers in evolutionary computation and swarm intelligence, though it is incremental as it builds on prior methods with extended simulations.
The study investigated long-term evolutionary dynamics in Swarm Chemistry by extending simulations and using an automated object harvesting method, finding that dynamics stabilized after an initial transient period and environmental perturbations significantly influenced trends, while the method generated a large collection of evolved objects to reveal autonomous creativity.
We studied the long-term dynamics of evolutionary Swarm Chemistry by extending the simulation length ten-fold compared to earlier work and by developing and using a new automated object harvesting method. Both macroscopic dynamics and microscopic object features were characterized and tracked using several measures. Results showed that the evolutionary dynamics tended to settle down into a stable state after the initial transient period, and that the extent of environmental perturbations also affected the evolutionary trends substantially. In the meantime, the automated harvesting method successfully produced a huge collection of spontaneously evolved objects, revealing the system's autonomous creativity at an unprecedented scale.