geoopt
evotorch
geoopt | evotorch | |
---|---|---|
2 | 14 | |
811 | 983 | |
2.2% | 1.5% | |
4.3 | 4.7 | |
about 2 months ago | 8 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
geoopt
-
A walk through of the functions used in "A Universal Model for Hyperbolic, Euclidean and Spherical Geometries" (the κ-Stereographic Model)
Looking at geoopt/manifolds/stereographic/math.py and trying to learn about hyperbolic geometry as I go, wondering if you could add some commentary to the functions. If anyone is in the mood to teach, I am all ears :). I can prompt with some questions, hopefully that will help clarify what is confusing or hard to understand for a newcomer.
-
Introducing Hyperlib: Simple Deep learning in Hyperbolic space [project]
Can you expand on this? What other toolkits already exist and how does yours solve the problems you saw in those frameworks? For example, maybe compare with https://github.com/geoopt/geoopt for one?
evotorch
- [P] EvoTorch 0.4.0 dropped with GPU-accelerated implementations of CMA-ES, MAP-Elites and NSGA-II.
-
Question on how to model a "discontinuous" action space
population based algos dont care about differentiability https://github.com/google/evojax https://github.com/RobertTLange/evosax https://github.com/nnaisense/evotorch https://github.com/uber-research/PyTorch-NEAT
- Should I pursue Evolutionary Strategies?
-
[P] We’ve released EvoTorch 0.3.0, with VecGymNE, memory usage improvements, Colab support and more! VecGymNE enables evolutionary RL with vectorized environments and policies, especially massively parallel simulators like Brax!
Check out the release and try it now: https://github.com/nnaisense/evotorch/releases/tag/v0.3.0
-
[P] Participating in the Myosuite challenge at NeurIPS2022 on dexterous control? We are releasing a baseline and starter code to help you get started using EvoTorch!
EvoTorch (evotorch.ai) makes it straightforward to apply evolutionary reinforcement learning to the challenge. We've included setup help, training and visualisation scripts, a baseline controller trained through the provided script and help for submission to the competition. Simply head to the public GitHub to get started: https://github.com/nnaisense/evotorch-myosuite-starter
-
NNAISENSE Open-Sources ‘EvoTorch’: An Evolutionary Algorithm Library for the Machine Learning Community
An Advanced Evolutionary library or algorithm has been a dream of scientists and AI/ML enthusiasts since the concept was introduced. This vision has come true thanks to the scientists at NNAISENSE, a Switzerland-based AI Enterprise. They created an open-source platform called EvoTorch. When operated in combination with Machine Learning, it can solve complex operational problems in a fraction of time, with lower costs, and at a larger scale. Evolutionary algorithms act as a step toward solving cascading problems that occur when the problem’s size and complexity increase. Evolutionary algorithms make the situations easier to handle the complexity without adding to the cost, they are also much easier to connect through GPUs and CPUs parallelly to ease up the calculation time and the complexity associated with it, that the only limit to your computational power becomes your budget. The evolutionary algorithms are built in the open framework EvoTorch.
- Next-Generation Evolutionary Search, Learning and Planning
- NNAISENSE releases EvoTorch (evotorch.ai): An open-source Evolutionary Algorithm Library with multi-CPU/multi-GPU support for massive evolutionary experiments!
- NNAISENSE releases EvoTorch: An open-source Evolutionary Algorithm Library with multi-CPU/multi-GPU support for massive evolutionary experiments!
What are some alternatives?
hyperlib - Library that contains implementations of machine learning components in the hyperbolic space
evojax
deep-neuroevolution - Deep Neuroevolution
de-torch - Minimal PyTorch Library for Differential Evolution
talk-generator - talk-generator is capable of generating coherent slide decks based on a single topic suggestion.
PyTorch-NEAT
pytorch-forecasting - Time series forecasting with PyTorch
pyshgp - Push Genetic Programming in Python.
evotorch-myosuite-starter
tiny_gp - Tiny Genetic Programming in Python
evolution-strategies-starter - Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"
SpaceDrones - A simple learning environment with space drones for evolution-inspired optimization.