Cellular Automata From First Principles 55: Run Parameter Sweeps and Benchmarks

Mon, 10 Aug 2026 20:58:00 +0100

Cellular Automata From First Principles 55: Run Parameter Sweeps and Benchmarks

Once experiments are reproducible, we can stop treating parameters as one-off choices and start mapping behavior systematically.

A parameter sweep is not merely a convenience.

It is a way to turn a model into a measurable landscape.

Build a grid of experiments

from itertools import product

mus = [0.12, 0.14, 0.16]
sigmas = [0.01, 0.02, 0.03]

configs = [
    {"mu": mu, "sigma": sigma, "seed": seed}
    for mu, sigma, seed in product(mus, sigmas, range(10))
]

Notice the seed axis.

Cellular Automata From First Principles 32: Search Lenia Parameter Space

Mon, 10 Aug 2026 19:57:00 +0100

Cellular Automata From First Principles 32: Search Lenia Parameter Space

A Lenia pattern is not defined by its initial state alone.

It also lives inside a particular dynamical world.

Change the kernel or growth function slightly and the same seed may:

die
explode
freeze
oscillate
move
split
stabilize into a different morphology

So discovery has two coupled search spaces:

initial condition
      +
world parameters

Define parameter ranges

PARAM_RANGES = {
    "radius": (8, 24),
    "ring_center": (0.25, 0.75),
    "ring_width": (0.05, 0.25),
    "mu": (0.05, 0.30),
    "sigma": (0.01, 0.08),
    "dt": (0.03, 0.20),
}

These ranges are experimental choices.

Parameter Search on Programmer.ie: Modern AI programming

Cellular Automata From First Principles 55: Run Parameter Sweeps and Benchmarks

Cellular Automata From First Principles 55: Run Parameter Sweeps and Benchmarks

Build a grid of experiments

Cellular Automata From First Principles 32: Search Lenia Parameter Space

Cellular Automata From First Principles 32: Search Lenia Parameter Space

Define parameter ranges