uber-research/deep-neuroevolution
Deep Neuroevolution
This project helps AI researchers and practitioners efficiently train deep neural networks for reinforcement learning tasks, such as teaching an AI to play Atari games or control a robot. It takes as input various neuroevolution algorithms and training configurations, and outputs optimized neural network models capable of performing complex actions in simulated environments. It also includes tools to visualize the training process, helping users understand how their AI models are evolving.
1,663 stars. No commits in the last 6 months.
Use this if you are an AI researcher or machine learning engineer experimenting with neuroevolution or genetic algorithms to train deep reinforcement learning agents and need distributed, scalable solutions.
Not ideal if you are looking for pre-trained AI models, a simple drag-and-drop solution for basic machine learning tasks, or if you are unfamiliar with reinforcement learning concepts and environment setup.
Stars
1,663
Forks
300
Language
Python
License
—
Category
Last pushed
Jan 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/uber-research/deep-neuroevolution"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
wagenaartje/neataptic
:rocket: Blazing fast neuro-evolution & backpropagation for the browser and Node.js
alenaksu/neatjs
NEAT (Neuro Evolution of Augmenting Topologies) implementation in JavaScript
liquidcarrot/carrot
🥕 Evolutionary Neural Networks in JavaScript
flxsosa/DeepHyperNEAT
A public python implementation of the DeepHyperNEAT system for evolving neural networks....
janhohenheim/Hippocrates
No longer maintained, actually usable implementation of NEAT