About
Compact implementation of Evolution Strategies using MPI, together with an MPI-based wrapper for the `cmaes' Python library (only parallelizing the function evaluations). This repository uses part of the code from OpenAI's implementation (https://github.com/openai/evolution-strategies-starter).
Example usage:
from esmpi import ES_MPI
def eval_fn(x):
time.sleep(0.01)
return (x[0] - 3) ** 2 + (10 * (x[1] + 2)) ** 2
optimizer = ES_MPI(n_params=2, population_size=16, learning_rate=0.1, sigma=0.02)
for i in range(50):
fit = optimizer.step(eval_fn)
if optimizer.is_master == 0:
print(f"{i}: fitness {np.mean(fit)}, current best params {optimizer.get_parameters()}\n")
1 maintainer
Metadata
1 maintainer
Release files for esmpi 1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| esmpi-1.0.tar.gz | 11.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| esmpi-1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 23.7 kB
Release files / esmpi-1.0.tar.gz
| Download URL | esmpi-1.0.tar.gz |
|---|---|
| Size | 11.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b266c75487531d68cc504794bafa3d7e8c6a065aa03282f58fb6b0ae511b6720
|
|
BLAKE2b-256 checksum How to use checksums |
6efaf1d674104bf374479e2766aa8021ef0c87c2ee0386447827108dd3c9a363
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.11.9
|
Release files / esmpi-1.0-py3-none-any.whl
| Download URL | esmpi-1.0-py3-none-any.whl |
|---|---|
| Size | 12.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2a6c1c0e078ce38c45a71c61e1974305d731bef7312762b033a4cd12743eb299
|
|
BLAKE2b-256 checksum How to use checksums |
c97fba8ca1bf74fe097d6fd259a0bc528820d7a410e2752c9f125b58b39eeb66
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.11.9
|
