Skip to main content

Minimal PyTorch Library for Natural Evolution Strategies

Project description

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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nes-torch-2.1.3.tar.gz (397.0 kB view details)

Uploaded Source

File details

Details for the file nes-torch-2.1.3.tar.gz.

File metadata

  • Download URL: nes-torch-2.1.3.tar.gz
  • Upload date:
  • Size: 397.0 kB
  • Tags: Source
  • Uploaded using 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

File hashes

Hashes for nes-torch-2.1.3.tar.gz
Algorithm Hash digest
SHA256 f4d8f6624608af03132807a8497f5677eeb7a1fef9f914eb984f0b95d0afeb22
MD5 31c4750b2f04fe0f91a762b152729a42
BLAKE2b-256 6d6a573ab28b6681005c2fa0cfdfa7af7ec1bf39628cad005c5acb942462c060

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page