Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
An open source framework for research in Embodied-AI from AI2.
| Date | Stars |
|---|---|
| 2026-07-24 | 382 |
| 2026-07-25 | 382 |
| 2026-07-28 | 382 |
| 2026-07-30 | 382 |
| 2026-08-06 | 382 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<img src="docs/img/AllenAct.svg" width="350" />
<br>
<i><h3>An open source framework for research in Embodied AI</h3></i>
</p>
<hr/>
</div>
[](./LICENSE)
[](https://allenact.org)
[](https://github.com/allenai/allenact/releases/latest)
[](https://www.python.org/downloads/release/python-360/)
[](https://lgtm.com/projects/g/allenai/allenact/context:python)
[](https://github.com/psf/black)
**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)](https://allenai.org/). AI2 is a non-profit institute with the mission to contribute to humanity through high-impact AI research and engineering.
## Quick Links
- [Website & Docs](https://www.allenact.org/)
- [Github](https://github.com/allenai/allenact)
- [Install](https://www.allenact.org/installation/installation-allenact/)
- [Tutorials](https://www.allenact.org/tutorials/)
- [AllenAct Paper](https://arxiv.org/abs/2008.12760)
- [Citation](#citation)
## Features & Highlights
* _Support for multiple environments_: Support for the [iTHOR](https://ai2thor.allenai.org/ithor/), [RoboTHOR](https://ai2thor.allenai.org/robothor/) and [Habitat](https://aihabitat.org/) embodied environments as well as for grid-worlds including [MiniGrid](https://github.com/maximecb/gym-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](https://arxiv.org/pdf/1707.06347.pdf), [DD-PPO](https://arxiv.org/pdf/1911.00357.pdf), [A2C](https://arxiv.org/pdf/1611.05763.pdf), Imitation Learning and [DAgger](https://www.ri.cmu.edu/pub_files/2011/4/Ross-AISTATS11-NoRegret.pdf) 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](https://ai2thor.allenai.org/ithor/), [RoboTHOR](https://ai2thor.allenai.org/robothor/), [Habitat](https://aihabitat.org/), [MiniGrid](https://github.com/maximecb/gym-minigrid), [OpenAI Gym](https://gym.openai.com/)|[PointNav](https://arxiv.org/pdf/1807.06757.pdf), [ObjectNav](https://arxiv.org/pdf/2006.13171.pdf), [MiniGrid tasks](https://github.com/maximecb/gym-minigrid), [Gym Box2D tasks](Excerpt of 6,098 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b8ffadaafc66706a, topic:reinforcement-learning, readme:imitation learning
matched fp:b8ffadaafc66706a, topic:deep-learning
matched fp:b8ffadaafc66706a, topic:computer-vision