Minimal PyTorch Library for Natural Evolution Strategies
Requirements
numpy
torch
Optional
gym # For gym examples
mpi4py # For parallelization
To install mpi4py you need MPI installed in the system.
Check: https://mpi4py.readthedocs.io/en/stable/install.html
A Dockerfile is provided for convenience.
Installation
pip install nes-torch --user
Documentation
https://nestorch.readthedocs.io/
Usage
See https://github.com/goktug97/nes-torch/blob/master/examples
Check documentation or https://github.com/goktug97/nes-torch/blob/master/nes/config.py for parameters.
You can run the example with
PYTHONPATH="$(pwd):$PYTHONPATH" python examples/example.py
or in parallel for faster training.
PYTHONPATH="$(pwd):$PYTHONPATH" mpirun --np 2 python examples/example.py
1 maintainer
Metadata
1 maintainer
Release files for nes-torch 2.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| nes-torch-2.1.3.tar.gz | 397.0 kB | Without provenance | Details for nes-torch-2.1.3.tar.gz |
Release files / nes-torch-2.1.3.tar.gz
| Download URL | nes-torch-2.1.3.tar.gz |
|---|---|
| Size | 397.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f4d8f6624608af03132807a8497f5677eeb7a1fef9f914eb984f0b95d0afeb22
|
|
BLAKE2b-256 checksum How to use checksums |
6d6a573ab28b6681005c2fa0cfdfa7af7ec1bf39628cad005c5acb942462c060
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.2 importlib_metadata/3.10.1 pkginfo/1.7.1 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7
|
Security for nes-torch 2.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
