https://github.com/allenai/allenact

An open source framework for research in Embodied-AI from AI2.

Science Score: 46.0%

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
✓
Academic publication links
Links to: arxiv.org
✓
Committers with academic emails
2 of 28 committers (7.1%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (14.9%) to scientific vocabulary

Keywords

ai ai2 computer-vision deep-learning embodied-agent python reinforcement-learning research

Keywords from Contributors

profiler transformation interactive genomics projection sequences archival embedded observability autograding

Last synced: 5 months ago · JSON representation

Repository

An open source framework for research in Embodied-AI from AI2.

Basic Info

Host: GitHub
Owner: allenai
License: other
Language: Python
Default Branch: main
Homepage: https://www.allenact.org
Size: 25.5 MB

Statistics

Stars: 367
Watchers: 9
Forks: 59
Open Issues: 56
Releases: 10

Topics

ai ai2 computer-vision deep-learning embodied-agent python reinforcement-learning research

Created about 6 years ago · Last pushed 6 months ago

Metadata Files

Readme Contributing License Roadmap

README.md

An open source framework for research in Embodied AI

AllenAct is a modular and flexible learning framework designed with a focus on the unique requirements of Embodied-AI research. It provides first-class support for a growing collection of embodied environments, tasks and algorithms, provides reproductions of state-of-the-art models and includes extensive documentation, tutorials, start-up code, and pre-trained models.

AllenAct is built and backed by the Allen Institute for AI (AI2). AI2 is a non-profit institute with the mission to contribute to humanity through high-impact AI research and engineering.

Quick Links

Features & Highlights

Support for multiple environments: Support for the iTHOR, RoboTHOR and Habitat embodied environments as well as for grid-worlds including MiniGrid.
Task Abstraction: Tasks and environments are decoupled in AllenAct, enabling researchers to easily implement a large variety of tasks in the same environment.
Algorithms: Support for a variety of on-policy algorithms including PPO, DD-PPO, A2C, Imitation Learning and DAgger as well as offline training such as offline IL.
Sequential Algorithms: It is trivial to experiment with different sequences of training routines, which are often the key to successful policies.
Simultaneous Losses: Easily combine various losses while training models (e.g. use an external self-supervised loss while optimizing a PPO loss).
Multi-agent support: Support for multi-agent algorithms and tasks.
Visualizations: Out of the box support to easily visualize first and third person views for agents as well as intermediate model tensors, integrated into Tensorboard.
Pre-trained models: Code and models for a number of standard Embodied AI tasks.
Tutorials: Start-up code and extensive tutorials to help ramp up to Embodied AI.
First-class PyTorch support: One of the few RL frameworks to target PyTorch.
Arbitrary action spaces: Supporting both discrete and continuous actions.

|Environments|Tasks|Algorithms| |------------|-----|----------| |iTHOR, RoboTHOR, Habitat, MiniGrid, OpenAI Gym|PointNav, ObjectNav, MiniGrid tasks, Gym Box2D tasks|A2C, PPO, DD-PPO, DAgger, Off-policy Imitation|

Contributions

We welcome contributions from the greater community. If you would like to make such a contributions we recommend first submitting an issue describing your proposed improvement. Doing so can ensure we can validate your suggestions before you spend a great deal of time upon them. Improvements and bug fixes should be made via a pull request from your fork of the repository at https://github.com/allenai/allenact.

All code in this repository is subject to formatting, documentation, and type-annotation guidelines. For more details, please see the our contribution guidelines.

Acknowledgments

This work builds upon the pytorch-a2c-ppo-acktr library of Ilya Kostrikov and uses some data structures from FAIR's habitat-lab. We would like to thank Dustin Schwenk for his help for the public release of the framework.

License

AllenAct is MIT licensed, as found in the LICENSE file.

Team

AllenAct is an open-source project built by members of the PRIOR research group at the Allen Institute for Artificial Intelligence (AI2).

Citation

If you use this work, please cite our paper:

bibtex @article{AllenAct, author = {Luca Weihs and Jordi Salvador and Klemen Kotar and Unnat Jain and Kuo-Hao Zeng and Roozbeh Mottaghi and Aniruddha Kembhavi}, title = {AllenAct: A Framework for Embodied AI Research}, year = {2020}, journal = {arXiv preprint arXiv:2008.12760}, }

Owner

Name: AI2
Login: allenai
Kind: organization
Email: ai2-info@allenai.org
Location: Seattle, WA

Website: http://www.allenai.org
Repositories: 454
Profile: https://github.com/allenai

GitHub Events

Total

Issues event: 2
Watch event: 34
Delete event: 1
Push event: 6
Fork event: 8
Create event: 1

Last Year

Issues event: 2
Watch event: 34
Delete event: 1
Push event: 6
Fork event: 8
Create event: 1

Committers

Last synced: over 1 year ago

All Time

Total Commits: 1,863
Total Committers: 28
Avg Commits per committer: 66.536
Development Distribution Score (DDS): 0.653

Past Year

Commits: 34
Committers: 4
Avg Commits per committer: 8.5
Development Distribution Score (DDS): 0.206

Top Committers

Name	Email	Commits
Jordi Salvador	j**s@a**g	647
klemenkotar	k**k@a**g	489
lucaw	l**w@a**g	411
Aniruddha Kembhavi	a**k@a**g	61
Klemen Kotar	k**n@k**s	44
Matt Deitke	m**3@g**m	42
Tianwei Ni	t**6@g**m	31
Klemen	k**n@l**n	28
KuoHaoZeng	k**g@a**g	27
Kiana Ehsani	e**k@g**m	12
Roozbeh Mottaghi	r**m@R**l	10
klemenk	k**k@k**l	9
apoorvkh	a**d@g**m	9
Eric Kolve	e**k@a**g	8
Roozbeh Mottaghi	r****m	7
jordis-ai2	3****2	5
mattdeitke	m**d@a**g	4
Zichen "Charles" Zhang	5****g	4
KuoHaoZeng	k**g@c**u	2
Luca Weihs	a**y@g**m	2
drschwenk	d**k@g**m	2
klemenk	k**k@i**l	2
dependabot[bot]	4****]	2
Ani Kembhavi	a**k@i**l	1
jiasenlu	j**u@g**u	1
Unnat Jain	u****t	1
LGTM Migrator	l****r	1
klemenk	k**k@i**l	1

Committer Domains (Top 20 + Academic)

allenai.org: 7 ip-172-16-36-152.us-west-2.compute.internal: 1 gatech.edu: 1 ip-10-0-0-227.us-west-2.compute.internal: 1 ip-172-16-3-136.us-west-2.compute.internal: 1 cs.washington.edu: 1 kotar.us: 1

Issues and Pull Requests

Last synced: 8 months ago

All Time

Total issues: 47
Total pull requests: 114
Average time to close issues: about 1 month
Average time to close pull requests: about 1 month
Total issue authors: 28
Total pull request authors: 14
Average comments per issue: 4.23
Average comments per pull request: 2.0
Merged pull requests: 70
Bot issues: 0
Bot pull requests: 20

Past Year

Issues: 3
Pull requests: 7
Average time to close issues: N/A
Average time to close pull requests: 5 days
Issue authors: 2
Pull request authors: 2
Average comments per issue: 0.0
Average comments per pull request: 0.29
Merged pull requests: 2
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

ShoufaChen (2)
hai-h-nguyen (2)
Aliiiranmanesh (2)
rxlqn (2)
pioneer-innovation (2)
qiwu57kevin (2)
npmhung (2)
joel99 (2)
twb1235 (2)
Hustwireless (1)
nbqu (1)
GracefulMan (1)
andykim0723 (1)
prithv1 (1)
rginjapan (1)

Pull Request Authors

Lucaweihs (24)
jordis-ai2 (17)
dependabot[bot] (15)
KuoHaoZeng (9)
twni2016 (8)
zcczhang (5)
mattdeitke (4)
Aakash-Roy (3)
apoorvkh (3)
ekolve (1)
lgtm-com[bot] (1)
kshitijd20 (1)
ehsanik (1)

Top Labels

Issue Labels

bug (13) enhancement (3) invalid (1)

Pull Request Labels

dependencies (15)

Packages

Total packages: 2
Total downloads:
- pypi 1,594 last-month

Total dependent packages: 0
(may contain duplicates)
Total dependent repositories: 8
(may contain duplicates)
Total versions: 32
Total maintainers: 1

pypi.org: allenact

AllenAct framework

Homepage: https://github.com/allenai/allenact
Documentation: https://allenact.readthedocs.io/
License: MIT
Latest release: 0.5.4
published about 2 years ago

Versions: 16
Dependent Packages: 0
Dependent Repositories: 6
Downloads: 811 Last month

Rankings

Stargazers count: 3.8%

Forks count: 6.0%

Dependent repos count: 6.1%

Average: 7.7%

Dependent packages count: 9.8%

Downloads: 13.0%

Maintainers (1)

allenact

Last synced: 6 months ago

pypi.org: allenact-plugins

Plugins for the AllenAct framework

Homepage: https://github.com/allenai/allenact
Documentation: https://allenact-plugins.readthedocs.io/
License: MIT
Latest release: 0.5.4
published about 2 years ago

Versions: 16
Dependent Packages: 0
Dependent Repositories: 2
Downloads: 783 Last month

Rankings

Stargazers count: 3.9%

Forks count: 6.0%

Average: 9.1%

Dependent packages count: 9.8%

Dependent repos count: 11.7%

Downloads: 13.9%

Maintainers (1)

allenact

Last synced: 6 months ago

Dependencies

allenact/setup.py pypi

Pillow >=8.2.0,<9.0.0
attrs >=21.4.0
filelock *
gym >=0.17.0,<0.20.0
matplotlib >=3.3.1
moviepy >=1.0.3
networkx *
numpy >=1.19.1
opencv-python *
scipy >=1.5.4
setproctitle *
tensorboardx >=2.1
torch >=1.6.0,
torchvision >=0.7.0
wheel >=0.36.2

allenact_plugins/babyai_plugin/extra_requirements.txt pypi

networkx *

allenact_plugins/clip_plugin/extra_requirements.txt pypi

ftfy *
regex *
torch >=1.7.1
torchvision *
tqdm *

allenact_plugins/gym_plugin/extra_requirements.txt pypi

gym >=0.17.0,<0.20.0

allenact_plugins/habitat_plugin/extra_requirements.txt pypi

numba *
numpy-quaternion *
pyquaternion >=0.9.9

allenact_plugins/ithor_plugin/extra_requirements.txt pypi

ai2thor >=2.5.3
colour *
numba *
numpy-quaternion *
packaging *
pyquaternion >=0.9.9
python-xlib *

allenact_plugins/lighthouse_plugin/extra_requirements.txt pypi

gym-minigrid >=1.0.1
patsy >=0.5.1

allenact_plugins/minigrid_plugin/extra_requirements.txt pypi

gym-minigrid >=1.0.1
patsy >=0.5.1
pickle5 *

allenact_plugins/robothor_plugin/extra_requirements.txt pypi

ai2thor >=2.5.3
colour *
numba *
numpy-quaternion *
packaging *
pyquaternion >=0.9.9
python-xlib *

allenact_plugins/setup.py pypi

allenact ==
gym >=0.17.0,<0.20.0
numpy >=1.19.1
torch >=1.6.0,
torchvision >=0.7.0
wheel >=0.36.2

dev_requirements.txt pypi

black ==19.10b0 development
compress-pickle ==1.2.0 development
docformatter ==1.3.1 development
docstr-coverage ==1.2.0 development
gitpython * development
markdown ==3.3 development
mkdocs ==1.1.2 development
mkdocs-material ==5.5.3 development
mypy * development
pre-commit * development
pydoc-markdown ==3.4.0 development
pytest * development
ruamel.yaml * development

requirements.txt pypi

Pillow >=8.2.0,<9.0.0
attr *
attrs *
certifi ==2020.12.5
chardet ==4.0.0
cloudpickle ==1.6.0
cycler ==0.10.0
decorator ==4.4.2
filelock ==3.0.12
future ==0.18.2
gym ==0.17.3
idna ==2.10
imageio ==2.9.0
imageio-ffmpeg ==0.4.3
kiwisolver ==1.3.1
matplotlib ==3.3.3
moviepy ==1.0.3
networkx ==2.5
numpy ==1.19.5
opencv-python ==4.5.1.48
proglog ==0.1.9
protobuf ==3.14.0
pyglet ==1.5.0
pyparsing ==2.4.7
python-dateutil >=2.8.1
requests ==2.25.1
scipy ==1.5.4
setproctitle ==1.2.1
six >=1.15.0
tensorboardX ==2.1
torch >=1.6.0,
torchvision >=0.7.0,<0.10.0
tqdm ==4.56.0
urllib3 ==1.26.5

.github/workflows/codeql.yml actions

actions/checkout v3 composite
github/codeql-action/analyze v2 composite
github/codeql-action/autobuild v2 composite
github/codeql-action/init v2 composite

.github/workflows/publish.yml actions

actions/checkout v2 composite
actions/setup-python v2 composite

.github/workflows/pytest.yml actions

actions/checkout v2 composite
actions/setup-python v2 composite
ouzi-dev/commit-status-updater v1.1.0 composite