SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1604.00772 · 2016

The CMA Evolution Strategy: A Tutorial

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1604.00772.json · badge: /api/ran/1604.00772.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
srom/cma-es community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
JohnYKiyo/coco_trial community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
fitness_fn Ran
ran on a synthesized input
srom/cma-es/notebook/tensorboard_example.py
code served (permissive licence) · get_code("70900b15f6128b0f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
import numpy as np

# Create a small batch of input data
# The function expects x with shape (batch_size, dimension)
# We'll use batch_size=2 and dimension=4
batch_size = 2
dimension = 4

# Create random input tensor with dtype float64 (as used in the function)
x_data = np.random.randn(batch_size, dimension).astype(np.float64)
x = tf.constant(x_data, dtype=tf.float64)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
objective Ran
ran on a synthesized input
JohnYKiyo/coco_trial/example.py
code served (permissive licence) · get_code("0d2817c655919766")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The objective function takes a single parameter x (a numeric value or array)
# and returns np.cos(1.5 * x) + 0.1 * x
# We need to provide a valid value for x

# x should be a numeric value or numpy array that can be used in the computation
x_value = np.array(2.5)

ARGS = {
    "x": x_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
plot_3d_surface Ran
ran on a synthesized input
srom/cma-es/notebook/utils/plot.py
code served (permissive licence) · get_code("eb399eb27455bb02")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf

# Define a simple fitness function that takes a tensor of shape (N, 2) and returns fitness values
def simple_fitness_fn(x):
    """Simple quadratic fitness function"""
    x_np = x.numpy() if isinstance(x, tf.Tensor) else x
    return tf.convert_to_tensor(np.sum(x_np**2, axis=1, keepdims=True), dtype=tf.float32)

# Create sample solutions (points in 2D space)
solutions = [
    np.array([0.5, 0.5]),
    np.array([-0.3, 0.7]),
    np.array([0.2, -0.4]),
    np.array([-0.6, -0.5])
]

# Mean point
mean = np.array([0.1, 0.2])

# Define the arguments dictionary
ARGS = {
    'fitness_fn': simple_fitness_fn,
    'xlim': (-1.0, 1.0),
    'ylim': (-1.0, 1.0),
    'zlim': (0.0, 2.0),
    'view_init': (30, 45),
    'mean': mean,
    'solutions': solutions,
    'show_axes': True,
    'fig': None,
    'ax': None,
    'figsize': (15, 8)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
plot_2d_contour Not yet run
unverified (harvested, no recorded run)
srom/cma-es/notebook/utils/plot.py
code served (permissive licence) · get_code("71a1a998f3e3d960")
How it ran

no invocation recorded.

plot_generations Not yet run
unverified (harvested, no recorded run)
srom/cma-es/notebook/utils/plot.py
code served (permissive licence) · get_code("c1800f95efd222ee")
How it ran

no invocation recorded.

test Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from ShangtongZhang/DistributedES
pointer only · get_code("0f3373194a3a7f49")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
test 1 other paper
1 later
1703.03864 (2017-03)
Evolution Strategies as a Scalable Alternative to Reinforcement Learning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This tutorial introduces the CMA Evolution Strategy (ES), where CMA stands for Covariance Matrix Adaptation. The CMA-ES is a stochastic, or randomized, method for real-parameter (continuous domain) optimization of non-linear, non-convex functions. We try to motivate and derive the algorithm from intuitive concepts and from requirements of non-linear, non-convex search in continuous domain.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1604.00772")
get_code_for_paper("1604.00772")
have("1604.00772")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1604.00772.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1604.00772.svg)](https://syntology.ai/paper/1604.00772)

Connect an agent — have() is free.