https://github.com/adaptive-intelligent-robotics/qdax

Accelerated Quality-Diversity

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 2 DOI reference(s) in README
✓
Academic publication links
Links to: arxiv.org, ieee.org, acm.org
✓
Committers with academic emails
6 of 18 committers (33.3%) from academic institutions
✓
Institutional organization owner
Organization adaptive-intelligent-robotics has institutional domain (www.imperial.ac.uk)
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (20.0%) to scientific vocabulary

Keywords

framework jax neuroevolution quality-diversity reinforcement-learning research

Last synced: 6 months ago · JSON representation

Repository

Accelerated Quality-Diversity

Basic Info

Host: GitHub
Owner: adaptive-intelligent-robotics
License: mit
Language: Python
Default Branch: main
Homepage: https://qdax.readthedocs.io/en/latest/
Size: 9.31 MB

Statistics

Stars: 313
Watchers: 6
Forks: 55
Open Issues: 30
Releases: 9

Topics

framework jax neuroevolution quality-diversity reinforcement-learning research

Created about 4 years ago · Last pushed 8 months ago

Metadata Files

Readme License

QDax: Accelerated Quality-Diversity

QDax is a tool to accelerate Quality-Diversity (QD) and neuroevolution algorithms through hardware accelerators and massive parallelization. QD algorithms usually take days/weeks to run on large CPU clusters. With QDax, QD algorithms can now be run in minutes! ⏩ ⏩ 🕛

QDax has been developed as a research framework: it is flexible and easy to extend and build on and can be used for any problem setting. Get started with simple example and run a QD algorithm in minutes here!

QDax paper
QDax documentation

Installation

QDax is available on PyPI and can be installed with: bash pip install qdax

To install QDax with CUDA 12 support, use: bash pip install qdax[cuda12]

Alternatively, the latest commit of QDax can be installed directly from source with: bash pip install git+https://github.com/adaptive-intelligent-robotics/QDax.git@main Installing QDax via pip installs a CPU-only version of JAX by default. To use QDax with NVidia GPUs, you must first install CUDA, CuDNN, and JAX with GPU support.

However, we also provide and recommend using either Docker or conda environments to use the repository which by default provides GPU support. Detailed steps to do so are available in the documentation.

Basic API Usage

For a full and interactive example to see how QDax works, we recommend starting with the tutorial-style Colab notebook. It is an example of the MAP-Elites algorithm used to evolve a population of controllers on a chosen Brax environment (Walker by default).

However, a summary of the main API usage is provided below: ```python import jax import functools from qdax.core.mapelites import MAPElites from qdax.core.containers.mapelitesrepertoire import computeeuclideancentroids from qdax.tasks.arm import armscoringfunction from qdax.core.emitters.mutationoperators import isolinevariation from qdax.core.emitters.standardemitters import MixingEmitter from qdax.utils.metrics import defaultqd_metrics

seed = 42 numparamdimensions = 100 # num DoF arm initbatchsize = 100 batchsize = 1024 numiterations = 50 gridshape = (100, 100) minparam = 0.0 maxparam = 1.0 mindescriptor = 0.0 max_descriptor = 1.0

Init a random key

key = jax.random.key(seed)

Init population of controllers

key, subkey = jax.random.split(key) initvariables = jax.random.uniform( subkey, shape=(initbatchsize, numparamdimensions), minval=minparam, maxval=max_param, )

Define emitter

variationfn = functools.partial( isolinevariation, isosigma=0.05, linesigma=0.1, minval=minparam, maxval=maxparam, ) mixingemitter = MixingEmitter( mutationfn=lambda x, y: (x, y), variationfn=variationfn, variationpercentage=1.0, batchsize=batch_size, )

Define a metrics function

metricsfn = functools.partial( defaultqdmetrics, qdoffset=0.0, )

Instantiate MAP-Elites

mapelites = MAPElites( scoringfunction=armscoringfunction, emitter=mixingemitter, metricsfunction=metrics_fn, )

Compute the centroids

centroids = computeeuclideancentroids( gridshape=gridshape, minval=mindescriptor, maxval=maxdescriptor, )

Initializes repertoire and emitter state

key, subkey = jax.random.split(key) repertoire, emitterstate, metrics = mapelites.init(init_variables, centroids, subkey)

Jit the update function for faster iterations

updatefn = jax.jit(mapelites.update)

Run MAP-Elites loop

for i in range(numiterations): key, subkey = jax.random.split(key) (repertoire, emitterstate, metrics,) = updatefn( repertoire, emitterstate, subkey, )

Get contents of repertoire

repertoire.genotypes, repertoire.fitnesses, repertoire.descriptors ```

QDax core algorithms

QDax currently supports the following algorithms:

| Algorithm | Example | |-------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | MAP-Elites | | | AURORA | | | CVT MAP-Elites | | | Policy Gradient Assisted MAP-Elites (PGA-ME) | | | DCRL-ME | | | QDPG | | | CMA-ME | | | OMG-MEGA | | | CMA-MEGA | | | Multi-Objective MAP-Elites (MOME) | | | MAP-Elites Evolution Strategies (MEES) | | | MAP-Elites PBT (ME-PBT) | | | MAP-Elites Low-Spread (ME-LS) | |

QDax baseline algorithms

The QDax library also provides implementations for some useful baseline algorithms:

| Algorithm | Example | | --- | --- | | DIAYN | | | DADS | | | SMERL | | | NSGA2 | | | SPEA2 | | | Population Based Training (PBT) | |

QDax Tasks

The QDax library also provides numerous implementations for several standard Quality-Diversity tasks.

All those implementations, and their descriptions are provided in the tasks directory.

Contributing

Issues and contributions are welcome. Please refer to the contribution guide in the documentation for more details.

Related Projects

EvoJAX: Hardware-Accelerated Neuroevolution. EvoJAX is a scalable, general purpose, hardware-accelerated neuroevolution toolkit. Paper
evosax: JAX-Based Evolution Strategies

Citing QDax

If you use QDax in your research and want to cite it in your work, please use: @article{chalumeau2024qdax, title={Qdax: A library for quality-diversity and population-based algorithms with hardware acceleration}, author={Chalumeau, Felix and Lim, Bryan and Boige, Raphael and Allard, Maxime and Grillotti, Luca and Flageat, Manon and Mac{\'e}, Valentin and Richard, Guillaume and Flajolet, Arthur and Pierrot, Thomas and others}, journal={Journal of Machine Learning Research}, volume={25}, number={108}, pages={1--16}, year={2024} }

Contributors

QDax was developed and is maintained by the Adaptive & Intelligent Robotics Lab (AIRL) and InstaDeep.

Owner

Name: Adaptive and Intelligent Robotics Lab
Login: adaptive-intelligent-robotics
Kind: organization
Location: Imperial College, London

Website: http://www.imperial.ac.uk/adaptive-intelligent-robotics
Repositories: 24
Profile: https://github.com/adaptive-intelligent-robotics

GitHub Events

Total

Create event: 10
Release event: 2
Issues event: 28
Watch event: 53
Delete event: 13
Issue comment event: 18
Push event: 50
Pull request review comment event: 25
Pull request review event: 32
Pull request event: 35
Fork event: 10

Last Year

Create event: 10
Release event: 2
Issues event: 28
Watch event: 53
Delete event: 13
Issue comment event: 18
Push event: 50
Pull request review comment event: 25
Pull request review event: 32
Pull request event: 35
Fork event: 10

Committers

Last synced: about 2 years ago

All Time

Total Commits: 129
Total Committers: 18
Avg Commits per committer: 7.167
Development Distribution Score (DDS): 0.589

Past Year

Commits: 26
Committers: 9
Avg Commits per committer: 2.889
Development Distribution Score (DDS): 0.654

Top Committers

Name	Email	Commits
Felix Chalumeau	f**u@i**m	53
Luca Grillotti	l**i@g**m	14
Luca Grillotti	l**6@i**k	13
Bryan Lim	4****n	9
Luca Grillotti	l**5@i**k	9
Manon Flageat	6****s	8
bryan	b**6@i**k	5
maxiallard	m**d@y**e	3
Maxime Allard	m**0@i**k	3
Manon Flageat	m**8@i**k	2
Maxime Allard	m**0@i**k	2
Bryon Tjanaka	3****a	2
Antoine Cully	a**y@h**m	1
Maxence Faldor	m**r@g**m	1
Thomas Pierrot	3****m	1
Raphaël Boige	4****b	1
David Braun	2****n	1
limbryan	l**9@g**m	1

Committer Domains (Top 20 + Academic)

ic.ac.uk: 3 imperial.ac.uk: 3 yahoo.de: 1 instadeep.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 78
Total pull requests: 93
Average time to close issues: 3 months
Average time to close pull requests: about 1 month
Total issue authors: 21
Total pull request authors: 18
Average comments per issue: 0.58
Average comments per pull request: 0.88
Merged pull requests: 69
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 15
Pull requests: 18
Average time to close issues: 3 months
Average time to close pull requests: 26 days
Issue authors: 6
Pull request authors: 6
Average comments per issue: 0.0
Average comments per pull request: 0.33
Merged pull requests: 10
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

felixchalumeau (33)
Lookatator (19)
MartinMao2023 (5)
manon-but-yes (4)
blacksph3re (3)
DBraun (2)
Aneoshun (2)
hannah-jan (2)
limbryan (2)
mplemay (1)
oilyraisin (1)
kayuksel (1)
miltonllera (1)
tcfuji (1)
btjanaka (1)

Pull Request Authors

Lookatator (33)
felixchalumeau (28)
manon-but-yes (10)
LisaCoiffard (6)
limbryan (5)
maxencefaldor (5)
hannah-jan (5)
TemplierPaul (5)
BioGeek (2)
btjanaka (2)
MartinMao2023 (2)
miltonllera (2)
mplemay (1)
DBraun (1)
eltociear (1)

Top Labels

Issue Labels

enhancement (19) bug (12) refactoring (5) good first issue (3) documentation (2) help wanted (1) metrics (1)

Pull Request Labels

enhancement (12) refactoring (4) bug (3) release (2) code update (2) documentation (1) metrics (1) CI (1)

Packages

Total packages: 3
Total downloads:
- pypi 2,461 last-month

Total dependent packages: 0
(may contain duplicates)
Total dependent repositories: 1
(may contain duplicates)
Total versions: 32
Total maintainers: 3

proxy.golang.org: github.com/adaptive-intelligent-robotics/QDax

Documentation: https://pkg.go.dev/github.com/adaptive-intelligent-robotics/QDax#section-documentation
License: mit
Latest release: v0.5.0
published 9 months ago

Versions: 11
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 6.5%

Average: 6.7%

Dependent repos count: 6.9%

Last synced: 6 months ago

proxy.golang.org: github.com/adaptive-intelligent-robotics/qdax

Documentation: https://pkg.go.dev/github.com/adaptive-intelligent-robotics/qdax#section-documentation
License: mit
Latest release: v0.5.0
published 9 months ago

Versions: 11
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 6.5%

Average: 6.7%

Dependent repos count: 6.9%

Last synced: 6 months ago

pypi.org: qdax

A Python Library for Quality-Diversity and NeuroEvolution

Homepage: https://github.com/adaptive-intelligent-robotics/QDax
Documentation: https://qdax.readthedocs.io/
License: MIT
Latest release: 0.5.0
published 9 months ago

Versions: 10
Dependent Packages: 0
Dependent Repositories: 1
Downloads: 2,461 Last month

Rankings

Stargazers count: 4.5%

Dependent packages count: 7.3%

Forks count: 8.1%

Downloads: 9.1%

Average: 10.2%

Dependent repos count: 22.1%

Maintainers (3)

AIRL felixchalumeau Lookatator

Last synced: 6 months ago

Dependencies

requirements.txt pypi

absl-py ==1.0.0
brax ==0.0.12
chex ==0.1.3
dm-haiku ==0.0.5
flax ==0.4.1
gym ==0.23.1
ipython *
jax ==0.3.10
jupyter *
numpy ==1.22.3
protobuf ==3.19.4
scikit-learn ==1.0.2
scipy ==1.8.0
seaborn ==0.11.2
sklearn ==0.0
tensorflow-probability ==0.15.0
typing-extensions ==3.10

docs/requirements.txt pypi

livereload ==2.6.3
mkdocs ==1.2.3
mkdocs-autorefs ==0.3.1
mkdocs-git-revision-date-plugin ==0.3.1
mkdocs-material ==8.2.3
mkdocstrings ==0.18.1
mknotebooks ==0.7.1

requirements-dev.txt pypi

coverage *
pre-commit ==2.12.1
pytest ==6.2.5
pytest-assume ==2.4.3

requirements-tool.txt pypi

pre-commit ==2.12.1

setup.py pypi

absl-py >=1.0.0
brax >=0.0.12
flax >=0.4.1
gym >=0.23.1
jax >=0.3.10
jaxlib >=0.3.10
numpy >=1.22.3
scikit-learn >=1.0.2
scipy >=1.8.0
sklearn *

.github/workflows/ci.yaml actions

FranzDiebold/github-env-vars-action v2 composite
actions/checkout v2 composite
codecov/codecov-action v2 composite
docker/build-push-action v3 composite
docker/login-action v2 composite
docker/metadata-action v4 composite
docker/setup-buildx-action v2 composite

environment.yaml pypi

https://github.com/adaptive-intelligent-robotics/qdax

Science Score: 67.0%

Keywords

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

QDax: Accelerated Quality-Diversity

Installation

Basic API Usage

Init a random key

Init population of controllers

Define emitter

Define a metrics function

Instantiate MAP-Elites

Compute the centroids

Initializes repertoire and emitter state

Jit the update function for faster iterations

Run MAP-Elites loop

Get contents of repertoire

QDax core algorithms

QDax baseline algorithms

QDax Tasks

Contributing

Related Projects

Citing QDax

Contributors

Owner

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

proxy.golang.org: github.com/adaptive-intelligent-robotics/QDax

Rankings

proxy.golang.org: github.com/adaptive-intelligent-robotics/qdax

Rankings

pypi.org: qdax

Rankings

Maintainers (3)

Dependencies