ribs 0.7.1

Description:

ribs 0.7.1

pyribs



Discord
Mailing List
Twitter





Google Groups







Website
Source
Docs
Paper




pyribs.org
GitHub
docs.pyribs.org
pyribs.org/paper






PyPI
Conda
CI/CD
Docs Status











A bare-bones Python library for quality diversity (QD) optimization. Pyribs
implements the highly modular Rapid Illumination of Behavior Space (RIBS)
framework for QD optimization. Pyribs is also the official implementation of
Covariance Matrix Adaptation MAP-Elites (CMA-ME), Covariance Matrix Adaptation
MAP-Elites via a Gradient Arborescence (CMA-MEGA), Covariance Matrix Adaptation
MAP-Annealing (CMA-MAE), and scalable variants of CMA-MAE.
Community
Join the
Pyribs Announcements mailing list for
infrequent updates (less than 1/month) on the status of the project and new
releases.
Need some help? Want to ask if pyribs is right for your project? Have a question
that is not quite a bug and not quite a feature request?
Join the community Discord!
Overview

Quality diversity (QD) optimization is a
subfield of optimization where solutions generated cover every point in a
measure space while simultaneously maximizing (or minimizing) a single
objective. QD algorithms within the MAP-Elites family of QD algorithms produce
heatmaps (archives) as output where each cell contains the best discovered
representative of a region in measure space.

In the QD literature, measure function outputs have also been referred to as
"behavioral characteristics," "behavior descriptors," or "feature
descriptors."

Recent years have seen the development of a large number of QD algorithms. To
represent these and future algorithms, we have developed the highly modular RIBS
framework. RIBS divides a QD algorithm into three components:

An archive, which saves generated solutions within measure space.
One or more emitters, where each emitter is an algorithm which generates
new candidate solutions and responds to feedback about how the solutions were
evaluated and how they were inserted into the archive.
A scheduler that controls the interaction of the archive and
emitters. The scheduler also provides an interface for requesting new
candidate solutions and telling the algorithm how candidates performed.

By interchanging these components, a user can compose a large number of QD
algorithms.
Pyribs is an implementation of the RIBS framework designed to support a wide
range of users, from beginners entering the field to experienced researchers
seeking to develop new algorithms. Pyribs achieves these goals by embodying
three principles:

Simple: Centered only on components that are absolutely necessary to run
a QD algorithm, allowing users to combine the framework with other software
frameworks.
Flexible: Capable of representing a wide range of current and future QD
algorithms, allowing users to easily create or modify components.
Accessible: Easy to install and learn, particularly for beginners with
limited computational resources.

In contrast to other QD libraries, pyribs is "bare-bones." For example, like
pycma, pyribs focuses solely on optimizing
fixed-dimensional continuous domains. Focusing on this one commonly-occurring
problem allows us to optimize the library for performance as well as ease of
use. Refer to the list of additional QD libraries
below if you need to handle additional use cases.
Following the RIBS framework (shown in the figure below), a standard algorithm
in pyribs operates as follows:

The user calls the ask() method on the scheduler. The scheduler requests
solutions from each emitter by calling the emitter's ask() method.
The user evaluates solutions to obtain the objective and measure values.
The user passes the evaluations to the scheduler's tell() method. The
scheduler adds the solutions into the archive and receives feedback. The
scheduler passes this feedback along with the evaluated solutions to each
emitter's tell() method, and each emitter then updates its internal state.


Installation
pyribs supports Python 3.8 and above. The vast majority of users can install
pyribs by running:
pip install ribs[visualize]

The command above includes the visualize extra. If you will not be using the
pyribs visualization tools, you can install the base version of pyribs with:
pip install ribs

For more specific installation commands (e.g., installing from Conda or
installing from source), visit the
installation selector on our website.
To test your installation, import pyribs and print the version with this
command:
python -c "import ribs; print(ribs.__version__)"

You should see a version number in the output.
Usage
Here we show an example application of CMA-ME in pyribs. To initialize the
algorithm, we first create:

A 2D GridArchive where each dimension contains 20 cells across the range
[-1, 1].
Three instances of EvolutionStrategyEmitter, all of which start from the
search point 0 in 10-dimensional space and a Gaussian sampling
distribution with standard deviation 0.1.
A Scheduler that combines the archive and emitters together.

After initializing the components, we optimize (pyribs maximizes) the negative
10-D Sphere function for 1000 iterations. Users of
pycma will be familiar with the ask-tell
interface (which pyribs adopted). First, the user must ask the scheduler for
new candidate solutions. After evaluating the solution, they tell the
scheduler the objectives and measures of each candidate solution. The algorithm
then populates the archive and makes decisions on where to sample solutions
next. Our toy example uses the first two parameters of the search space as
measures.
import numpy as np

from ribs.archives import GridArchive
from ribs.emitters import EvolutionStrategyEmitter
from ribs.schedulers import Scheduler

archive = GridArchive(
solution_dim=10,
dims=[20, 20],
ranges=[(-1, 1), (-1, 1)],
)
emitters = [
EvolutionStrategyEmitter(
archive,
x0=[0.0] * 10,
sigma0=0.1,
) for _ in range(3)
]
scheduler = Scheduler(archive, emitters)

for itr in range(1000):
solutions = scheduler.ask()

# Optimize the 10D negative Sphere function.
objective_batch = -np.sum(np.square(solutions), axis=1)

# Measures: first 2 coordinates of each 10D solution.
measures_batch = solutions[:, :2]

scheduler.tell(objective_batch, measures_batch)

To visualize this archive with Matplotlib, we then use the
grid_archive_heatmap function from ribs.visualize.
import matplotlib.pyplot as plt
from ribs.visualize import grid_archive_heatmap

grid_archive_heatmap(archive)
plt.show()


Documentation
The documentation is available online here. We
suggest that new users start with the
tutorials.
Paper and Citation
Two years after the initial release of pyribs, we released a paper that
elaborates on the RIBS framework and the design decisions behind pyribs. For
more information on this paper, see here. If you use
pyribs in your research, please consider citing this paper as follows. Also
consider citing any algorithms you use as shown
below.
@inproceedings{10.1145/3583131.3590374,
author = {Tjanaka, Bryon and Fontaine, Matthew C and Lee, David H and Zhang, Yulun and Balam, Nivedit Reddy and Dennler, Nathaniel and Garlanka, Sujay S and Klapsis, Nikitas Dimitri and Nikolaidis, Stefanos},
title = {Pyribs: A Bare-Bones Python Library for Quality Diversity Optimization},
year = {2023},
isbn = {9798400701191},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3583131.3590374},
doi = {10.1145/3583131.3590374},
abstract = {Recent years have seen a rise in the popularity of quality diversity (QD) optimization, a branch of optimization that seeks to find a collection of diverse, high-performing solutions to a given problem. To grow further, we believe the QD community faces two challenges: developing a framework to represent the field's growing array of algorithms, and implementing that framework in software that supports a range of researchers and practitioners. To address these challenges, we have developed pyribs, a library built on a highly modular conceptual QD framework. By replacing components in the conceptual framework, and hence in pyribs, users can compose algorithms from across the QD literature; equally important, they can identify unexplored algorithm variations. Furthermore, pyribs makes this framework simple, flexible, and accessible, with a user-friendly API supported by extensive documentation and tutorials. This paper overviews the creation of pyribs, focusing on the conceptual framework that it implements and the design principles that have guided the library's development. Pyribs is available at https://pyribs.org},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference},
pages = {220–229},
numpages = {10},
keywords = {framework, quality diversity, software library},
location = {Lisbon, Portugal},
series = {GECCO '23}
}

Contributors
pyribs is developed and maintained by the ICAROS Lab at
USC. For information on contributing to the repo, see
CONTRIBUTING.

Bryon Tjanaka
Matthew C. Fontaine
David H. Lee
Yulun Zhang
Nivedit Reddy Balam
Nathan Dennler
Sujay S. Garlanka
Nikitas Klapsis
Robby Costales
Sam Sommerer
Vincent Vu
Stefanos Nikolaidis

We thank Amy K. Hoover and
Julian Togelius for their contributions deriving
the CMA-ME algorithm.
Users
pyribs users include:


Adam Gaier (Autodesk Research)
Adaptive & Intelligent Robotics Lab (Imperial College London)
Chair of Statistical Learning and Data Science (LMU Munich)
Game Innovation Lab (New York University)
Giovanni Iacca (University of Trento)
HUAWEI Noah's Ark Lab
ICAROS Lab (University of Southern California)
Jacob Schrum (Southwestern University)
Lenia Research
Paul Kent (The University of Warwick)
Various
researchers at the
University of Tsukuba

Publications
For the list of publications that use pyribs, refer to our
Google Scholar entry.
Software
See the
GitHub dependency graph
for the public GitHub repositories which depend on pyribs.
Citing Algorithms in pyribs
If you use the following algorithms, please consider citing their relevant
papers:

CMA-ME: Fontaine 2020
@inproceedings{10.1145/3377930.3390232,
author = {Fontaine, Matthew C. and Togelius, Julian and Nikolaidis, Stefanos and Hoover, Amy K.},
title = {Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space},
year = {2020},
isbn = {9781450371285},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3377930.3390232},
doi = {10.1145/3377930.3390232},
booktitle = {Proceedings of the 2020 Genetic and Evolutionary Computation Conference},
pages = {94–102},
numpages = {9},
location = {Canc\'{u}n, Mexico},
series = {GECCO '20}
}


CMA-MEGA:
Fontaine 2021
@inproceedings{NEURIPS2021_532923f1,
author = {Fontaine, Matthew and Nikolaidis, Stefanos},
booktitle = {Advances in Neural Information Processing Systems},
editor = {M. Ranzato and A. Beygelzimer and Y. Dauphin and P.S. Liang and J. Wortman Vaughan},
pages = {10040--10052},
publisher = {Curran Associates, Inc.},
title = {Differentiable Quality Diversity},
url = {https://proceedings.neurips.cc/paper/2021/file/532923f11ac97d3e7cb0130315b067dc-Paper.pdf},
volume = {34},
year = {2021}
}


CMA-MAE: Fontaine 2022
@misc{cmamae,
doi = {10.48550/ARXIV.2205.10752},
url = {https://arxiv.org/abs/2205.10752},
author = {Fontaine, Matthew C. and Nikolaidis, Stefanos},
keywords = {Machine Learning (cs.LG), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Covariance Matrix Adaptation MAP-Annealing},
publisher = {arXiv},
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}


Scalable CMA-MAE: Tjanaka 2022
@ARTICLE{10243102,
author={Tjanaka, Bryon and Fontaine, Matthew C. and Lee, David H. and Kalkar, Aniruddha and Nikolaidis, Stefanos},
journal={IEEE Robotics and Automation Letters},
title={Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealing},
year={2023},
volume={8},
number={10},
pages={6771-6778},
keywords={Covariance matrices;Training;Neural networks;Legged locomotion;Reinforcement learning;Evolutionary robotics;Evolutionary robotics;reinforcement learning},
doi={10.1109/LRA.2023.3313012}
}



Additional QD Libraries

QDax: Implementations
of QD algorithms in JAX. QDax is suitable if you want to run entire QD
algorithms on hardware accelerators in a matter of minutes, and it is
particularly useful if you need to interface with Brax environments.
qdpy: Python implementations of a
wide variety of QD algorithms.
sferes: Contains C++ implementations of
QD algorithms; can also handle discrete domains.

License
pyribs is released under the
MIT License.
Credits
The pyribs package was initially created with
Cookiecutter and the
audreyr/cookiecutter-pypackage
project template.
History
0.7.1
This release introduces the
QDHF tutorial! It also
makes a couple of minor usability improvements, such as better error checking.
Changelog
API

Support Python 3.12 ({pr}390)

Improvements

Add qd score to lunar lander example ({pr}458)
Raise error if result_archive and archive have different fields
({pr}461)
Warn user if resampling for bounds takes too long in ESs ({pr}462)

Documentation

Add QDHF tutorial ({pr}459)

Bugs

Fix solution retrieval in lunar lander eval ({pr}457)

0.7.0
To learn about this release, see our page on What's New in v0.7.0:
https://docs.pyribs.org/en/stable/whats-new.html
Changelog
API

Support alternative centroid generation methods in CVTArchive ({pr}417,
{pr}437)
Add PyCMAEvolutionStrategy for using pycma in ES emitters ({pr}434)
Backwards-incompatible: Add ranking values to evolution strategy tell
method ({pr}438)
Backwards-incompatible: Move evolution strategy bounds to init ({pr}436)
Backwards-incompatible: Use seed instead of rng in ranker ({pr}432)
Backwards-incompatible: Replace status and value with add_info ({pr}430)
Support custom data fields in archive, emitters, and scheduler ({pr}421,
{pr}429)
Backwards-incompatible: Remove _batch from parameter names ({pr}422,
{pr}424, {pr}425, {pr}426, {pr}428)
Add Gaussian, IsoLine Operators and Refactor GaussianEmitter/IsoLineEmitter
({pr}418)
Backwards-incompatible: Remove metadata in favor of custom fields
({pr}420)
Add Base Operator Interface and Emitter Operator Retrieval ({pr}416)
Backwards-incompatible: Return occupied booleans in retrieve ({pr}414)
Backwards-incompatible: Deprecate as_pandas in favor of
data(return_type="pandas") ({pr}408)
Backwards-incompatible: Replace ArchiveDataFrame batch methods with
get_field ({pr}413)
Add field_list and data methods to archives ({pr}412)
Include threshold in archive.best_elite ({pr}409)
Backwards-incompatible: Replace Elite and EliteBatch with dicts
({pr}397)
Backwards-incompatible: Rename measure_* columns to measures_* in
as_pandas ({pr}396)
Add ArrayStore data structure ({pr}395, {pr}398, {pr}400, {pr}402,
{pr}403, {pr}404, {pr}406, {pr}407, {pr}411)
Add GradientOperatorEmitter to support OMG-MEGA and OG-MAP-Elites ({pr}348)

Improvements

Raise error when threshold_min is set but learning_rate is not ({pr}453)
Fix interval_size in CVTArchive and SlidingBoundariesArchive ({pr}452)
Allow overriding ES in sphere example ({pr}439)
Use NumPy SeedSequence in emitters ({pr}431, {pr}440)
Use numbers types when checking arguments ({pr}419)
Reimplement ArchiveBase using ArrayStore ({pr}399)
Use chunk computation in CVT brute force calculation to reduce memory usage
({pr}394)
Test pyribs installation in tutorials ({pr}384)
Add cron job for testing installation ({pr}389, {pr}401)
Fix broken cross-refs in docs ({pr}393)

Documentation

Tidy up LSI MNIST notebook ({pr}444)

0.6.4
Small release that adds the scalable CMA-MAE tutorial.
Changelog
Documentation

Add tutorial on scalable CMA-MAE variants ({pr}433, {pr}443)

0.6.3
Small patch release due to deprecation issues.
Changelog
Improvements

Replace np.product with np.prod due to deprecation ({pr}385)

0.6.2
Small patch release due to installation issues in our tutorials.
Changelog
API

Import ribs[visualize] in tutorials that need it ({pr}379)

Improvements

Switch to a branch-based release model ({pr}382)

0.6.1
(This release was removed)
0.6.0
Changelog
API

Drop Python 3.7 support and upgrade dependencies ({pr}350)
Add visualization of QDax repertoires ({pr}353)
Improve cvt_archive_heatmap flexibility ({pr}354)
Clip Voronoi regions in cvt_archive_heatmap ({pr}356)
Backwards-incompatible: Allow using kwargs for colorbar in
parallel_axes_plot ({pr}358)

Removes cbar_orientaton and cbar_pad args for parallel_axes_plot


Add rasterized arg for heatmaps ({pr}359)
Support 1D cvt_archive_heatmap ({pr}362)
Add 3D plots for CVTArchive ({pr}371)
Add visualization of 3D QDax repertoires ({pr}373)
Enable plotting custom data in visualizations ({pr}374)

Documentation

Use dask instead of multiprocessing for lunar lander tutorial ({pr}346)
pip install swig before gymnasium[box2d] in lunar lander tutorial ({pr}346)
Fix lunar lander dependency issues ({pr}366, {pr}367)
Simplify DQD tutorial imports ({pr}369)
Improve visualization docs examples ({pr}372)

Improvements

Improve developer workflow with pre-commit ({pr}351, {pr}363)
Speed up 2D cvt_archive_heatmap by order of magnitude ({pr}355)
Refactor visualize module into multiple files ({pr}357)
Refactor visualize tests into multiple files ({pr}370)
Add GitHub link roles in documentation ({pr}361)
Refactor argument validation utilities ({pr}365)
Use Conda envs in all CI jobs ({pr}368)
Split tutorial CI into multiple jobs ({pr}375)

0.5.2
This release contains miscellaneous edits to our documentation from v0.5.1.
Furthermore, the library is updated to support Python 3.11, removed deprecated
options, and strengthened with more robust checks and error messages in the
schedulers.
Changelog
API

Support Python 3.11 ({pr}342)
Check that emitters passed in are lists/iterables in scheduler ({pr}341)
Fix Matplotlib get_cmap deprecation ({pr}340)
Backwards-incompatible: Default plot_centroids to False when plotting
({pr}339)
Raise error messages when ask is called without ask_dqd ({pr}338)

Documentation

Add BibTex citation for GECCO 2023 ({pr}337)

Improvements

Update distribution dependencies ({pr}344)

0.5.1
This release contains miscellaneous edits to our documentation from v0.5.0.
There were no changes to library functionality in this release.
0.5.0
To learn about this release, see our page on What's New in v0.5.0:
https://docs.pyribs.org/en/stable/whats-new.html
Changelog
API

Schedulers warn if no solutions are inserted into archive ({pr}320)
Implement BanditScheduler ({pr}299)
Backwards-incompatible: Implement Scalable CMA-ES Optimizers ({pr}274,
{pr}288)
Make ribs.emitters.opt public ({pr}281)
Add normalized QD score to ArchiveStats ({pr}276)
Backwards-incompatible: Make ArchiveStats a dataclass ({pr}275)
Backwards-incompatible: Add shape checks to tell() and tell_dqd()
methods ({pr}269)
Add method for computing CQD score in archives ({pr}252)
Backwards-incompatible: Deprecate positional arguments in constructors
({pr}261)
Backwards-incompatible: Allow custom initialization in Gaussian and
IsoLine emitters ({pr}259, {pr}265)
Implement CMA-MAE archive thresholds ({pr}256, {pr}260, {pr}314)

Revive the old implementation of add_single removed in ({pr}221)
Add separate tests for add_single and add with single solution


Fix all examples and tutorials ({pr}253)
Add restart timer to EvolutionStrategyEmitter and
GradientArborescenceEmitter({pr}255)
Rename fields and update documentation ({pr}249, {pr}250)

Backwards-incompatible: rename Optimizer to Scheduler
Backwards-incompatible: rename objective_value to objective
Backwards-incompatible: rename behavior_value/bcs to measures
Backwards-incompatible: behavior_dim in archives is now measure_dim
Rename n_solutions to batch_size in Scheduler.


Add GradientArborescenceEmitter, which is used to implement CMA-MEGA
({pr}240, {pr}263, {pr}264, {pr}282, {pr}321)
Update emitter tell() docstrings to no longer say "Inserts entries into
archive" ({pr}247)
Expose emitter.restarts as a property ({pr}248)
Specify that x0 is 1D for all emitters ({pr}244)
Add best_elite property for archives ({pr}237)
Rename methods in ArchiveDataFrame and rename as_pandas behavior columns
({pr}236)
Re-run CVTArchive benchmarks and update CVTArchive ({pr}235, {pr}329)

Backwards-incompatible: use_kd_tree now defaults to True since the k-D
tree is always faster than brute force in benchmarks.


Allow adding solutions one at a time in optimizer ({pr}233)
Minimize numba usage ({pr}232)
Backwards-incompatible: Implement batch addition in archives ({pr}221,
{pr}242)

add now adds a batch of solutions to the archive
add_single adds a single solution


emitter.tell now takes in status_batch and value_batch ({pr}227)
Make epsilon configurable in archives ({pr}226)
Backwards-incompatible: Remove ribs.factory ({pr}225, {pr}228)
Backwards-incompatible: Replaced ImprovementEmitter,
RandomDirectionEmitter, and OptimizingEmitter with
EvolutionStrategyEmitter ({pr}220, {pr}223, {pr}278)
Raise ValueError for incorrect array shapes in archive methods ({pr}219)
Introduced the Ranker object, which is responsible for ranking the solutions
based on different objectives ({pr}209, {pr}222, {pr}245)
Add index_of_single method for getting index of measures for one solution
({pr}214)
Backwards-incompatible: Replace elite_with_behavior with retrieve and
retrieve_single in archives ({pr}213, {pr}215, {pr}295)
Backwards-incompatible: Replace get_index with batched index_of method in
archives ({pr}208)

Also added grid_to_int_index and int_to_grid_index methods for
GridArchive and SlidingBoundariesArchive


Backwards-incompatible: Made it such that each archive is initialized
fully in its constructor instead of needing a separate
.initialize(solution_dim) call ({pr}200)
Backwards-incompatible: Add sigma, sigma0 options to
gaussian_emitter and iso_line_emitter ({pr}199)

gaussian_emitter constructor requires sigma; sigma0 is optional.
iso_line_emitter constructor takes in optional parameter sigma0.


Backwards-incompatible: Add cbar, aspect options for
cvt_archive_heatmap ({pr}197)
Backwards-incompatible: Add aspect option to grid_archive_heatmap +
support for 1D heatmaps ({pr}196)

square option no longer works


Backwards-incompatible: Add cbar option to grid_archive_heatmap
({pr}193)
Backwards-incompatible: Replace get_random_elite() with batched
sample_elites() method ({pr}192)
Backwards-incompatible: Add EliteBatch and rename fields in Elite
({pr}191)
Backwards-incompatible: Rename bins to cells for consistency with
literature ({pr}189)

Archive constructors now take in cells argument instead of bins
Archive now have a cells property rather than a bins property


Backwards-incompatible: Only use integer indices in archives ({pr}185)

ArchiveBase

Replaced storage_dims (tuple of int) with storage_dim (int)
_occupied_indices is now a fixed-size array with _num_occupied
indicating its current usage, and _occupied_indices_cols has been
removed
index_of must now return an integer





Bugs

Fix boundary lines in sliding boundaries archive heatmap ({pr}271)
Fix negative eigenvalue in CMA-ES covariance matrix ({pr}285)

Documentation

Speed up lunar lander tutorial ({pr}319)
Add DQDTutorial ({pr}267)
Remove examples extra in favor of individual example deps ({pr}306)
Facilitate linking to latest version of documentation ({pr}300)
Update lunar lander tutorial with v0.5.0 features ({pr}292)
Improve tutorial and example overviews ({pr}291)
Move tutorials out of examples folder ({pr}290)
Update lunar lander to use Gymnasium ({pr}289)
Add CMA-MAE tutorial ({pr}273, {pr}284)
Update README ({pr}279)
Add sphinx-codeautolink to docs ({pr}206, {pr}280)
Fix documentation rendering issues on ReadTheDocs ({pr}205)
Fix typos and formatting in docstrings of ribs/visualize.py ({pr}203)
Add in-comment type hint rich linking ({pr}204)
Upgrade Sphinx dependencies ({pr}202)

Improvements

Move threadpoolctl from optimizer to CMA-ES ({pr}241)
Remove unnecessary emitter benchmarks ({pr}231)
Build docs during CI/CD workflow ({pr}211)
Drop Python 3.6 and add Python 3.10 support ({pr}181)
Add procedure for updating changelog ({pr}182)
Add 'visualize' extra ({pr}183, {pr}184, {pr}302)

0.4.0 (2021-07-19)
To learn about this release, see our blog post: https://pyribs.org/blog/0-4-0
Changelog
API

Add ribs.visualize.parallel_axes_plot for analyzing archives with
high-dimensional BCs ({pr}92)
Backwards-incompatible: Reduce attributes and parameters in EmitterBase to
make it easier to extend ({pr}101)
In Optimizer, support emitters that return any number of solutions in ask()
({pr}101)
Backwards-incompatible: Store metadata in archives as described in
{pr}87 ({pr}103, {pr}114, {pr}115, {pr}119)
Backwards-incompatible: Rename "index" to "index_0" in
CVTArchive.as_pandas for API consistency ({pr}113)
Backwards-incompatible: Make index_of() public in archives to emphasize
each index's meaning ({pr}128)
Backwards-incompatible: Add index to get_random_elite() and
elite_with_behavior() in archives ({pr}129)
Add clear() method to archive ({pr}140, {pr}146)
Represent archive elites with an Elite namedtuple ({pr}142)
Add len and iter methods to archives ({pr}151, {pr}152)
Add statistics to archives ({pr}100, {pr}157)
Improve manipulation of elites by modifying as_pandas ({pr}123, {pr}149,
{pr}153, {pr}158, {pr}168)
Add checks for optimizer array and list shapes ({pr}166)

Documentation

Add bibtex citations for tutorials ({pr}122)
Remove network training from Fooling MNIST tutorial ({pr}161)
Fix video display for lunar lander in Colab ({pr}163)
Fix Colab links in stable docs ({pr}164)

Improvements

Add support for Python 3.9 ({pr}84)
Test with pinned versions ({pr}110)
Increase minimum required versions for scipy and numba ({pr}110)
Refactor as_pandas tests ({pr}114)
Expand CI/CD to test examples and tutorials ({pr}117)
Tidy up existing tests ({pr}120, {pr}127)
Fix vocab in various areas ({pr}138)
Fix dependency issues in tests ({pr}139)
Remove tox from CI ({pr}143)
Replace "entry" with "elite" in tests ({pr}144)
Use new archive API in ribs.visualize implementation ({pr}155)

0.3.1 (2021-03-05)
This release features various bug fixes and improvements. In particular, we have
added tests for SlidingBoundariesArchive and believe it is ready for more
rigorous use.
Changelog

Move SlidingBoundariesArchive out of experimental by adding tests and fixing
bugs ({pr}93)
Added nicer figures to the Sphere example with grid_archive_heatmap
({pr}86)
Added testing for Windows and MacOS ({pr}83)
Fixed package metadata e.g. description

0.3.0 (2021-02-05)
pyribs is now in beta. Since our alpha release (0.2.0), we have polished the
library and added new tutorials and examples to our documentation.
Changelog

Added a Lunar Lander example that extends the lunar lander tutorial ({pr}70)
Added New Tutorial: Illuminating the Latent Space of an MNIST GAN ({pr}78)
GridArchive: Added a boundaries attribute with the upper and lower bounds of
each dimension's bins ({pr}76)
Fixed a bug where CMA-ME emitters do not work with float32 archives ({pr}74)
Fixed a bug where Optimizer is able to take in non-unique emitter instances
({pr}75)
Fixed a bug where GridArchive failed for float32 due to a small epsilon
({pr}81)
Fix issues with bounds in the SlidingBoundaryArchive ({pr}77)
Added clearer error messages for archives ({pr}82)
Modified the Python requirements to allow any version above 3.6.0 ({pr}68)
The wheel is now fixed so that it only supports py3 rather than py2 and py3
({pr}68)
Miscellaneous documentation fixes ({pr}71)

0.2.0 (2021-01-29)

Alpha release

0.2.1 (2021-01-29)

Package metadata fixes (author, email, url)
Miscellaneous documentation improvements

0.1.1 (2021-01-29)

Test release (now removed)

0.1.0 (2020-09-11)

Test release (now removed)

0.0.0 (2020-09-11)

pyribs begins