Pyribs v0.8.0 is now available! @pyribs v0.8.0 adds support for new algorithms (Novelty Search, BOP-Elites, and Density Descent Search), while making it easier than ever to design new ones 🧠 Here are the highlights 🧵
Daily @pyribs tweet #1: My favorite part of the lunar lander tutorial is how fast it became. The first version took 2 hrs to run, but by reducing the CMA-ME iterations and integrating Dask, it now runs in ~20 min! Fast runtime is important for a tutorial that all users start with
We are excited to announce the release of @pyribs v0.5.0! Pyribs v0.5.0 brings a slew of new features, tutorials, and improvements!
Installation: pip install ribs (our Conda package will be ready in a week or two)
Website: https://t.co/a8oLLICoR7
GitHub: https://t.co/0ufRXe01IO
pyribs 0.4.0 is live! It has many new features (some backwards-incompatible); here we cover a few. See our blog https://t.co/i1stZrqpBM for more info. 1/7
That’s all for now! We recommend taking a look at the blog to check if any of our backwards-incompatible changes affect you https://t.co/i1stZrqpBM 6/7
Excited to share some recent work with @snikolaidis19 on differentiable quality diversity (DQD).
pdf: https://t.co/7Js2BrZfw9
abs: https://t.co/CTv6MkJiS2
code: https://t.co/pAykoLxBPN
Announcing pyribs 0.3.1! This is a patch release. In particular, we have added tests for the SlidingBoundariesArchive and believe it is ready for more rigorous use.
pyribs is now on Conda thx to @condaforge! Get the full dist (same as "pip install ribs[all]") with:
conda install -c conda-forge pyribs
For the base dist (same as "pip install ribs"):
conda install -c conda-forge pyribs-base
See our blog for more info https://t.co/pij9NXsVc9