Evolving Neural Networks through Augmenting Topologies withEvolution Strategy Training
Project description
NEATEST: Evolving Neural Networks Through Augmenting Topologies with Evolution Strategy Training
It is NEAT but the weights are trained with Natural Evolution Strategy and the weights are shared across genomes.
Requirements
numpy
cloudpickle
Install
pip install nesneat
Optional
matplotlib # To draw networks
mpi4py # For parallelization
gym # For examples
Usage
Check examples
PYTHONPATH="$(pwd):$PYTHONPATH" python examples/cartpole.py
# Or in parallel
PYTHONPATH="$(pwd):$PYTHONPATH" mpirun -np 2 python examples/cartpole.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
nesneat-1.0.7.tar.gz
(5.4 MB
view details)
File details
Details for the file nesneat-1.0.7.tar.gz
.
File metadata
- Download URL: nesneat-1.0.7.tar.gz
- Upload date:
- Size: 5.4 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/3.10.1 pkginfo/1.7.0 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.61.1 CPython/3.9.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d47a4c5450f6267864928a499436a72ddc647cb41592d391f9b2fe79390d7ea9 |
|
MD5 | de3e37bfe4ad7e92ef07f97883444ee5 |
|
BLAKE2b-256 | 2cb9918673c901b0727d9f88ec73a21cfb6879f65022950ad1f422a4955968c6 |