---
title: CoRL
---
<!-- {{ include_top_banner() }} -->
<!-- {{ include_github_badges() }} -->
<!-- {{ include_repo_badges() }} -->
# 1. Core ACT3 Reinforcement Learning Library
> **This repository and corresponding documentation site are currently under construction. We are still porting items and updating instructions for GitHub.**
## 1.1. Summary
The Core ACT3 Reinforcement Learning library (CoRL) is created and maintained by the Air Force Research Laboratory’s (AFRL) [Autonomy Capability Team (ACT3)](https://www.afrl.af.mil/ACT3/). CoRL is intended to enable scalable deep reinforcement learning (RL) experimentation in a manner extensible to new simulations and new ways for the learning agents to interact with them. The objective is to make RL research easier by removing lock-in to particular simulations.
### 1.1.1. Benefits
- Makes RL environment development significantly easier
- Provides hyper configurable environments, agents and experiments
- Record observations by adding a few lines of config (instead of creating a new file for each observation)
- Reuse glues/dones/rewards between different tasks if they are general
- Uses an episode parameter provider (EPP) to randomize both domain and curriculum learning
- Has an integration first focus, which means that integrating agents to the real world or different simulators is significantly easier
### 1.1.2. Related Publications
- [CoRL: Environment Creation and Management Focused on System Integration](https://arxiv.org/abs/2303.02182)
- [Inside the special F-16 the Air Force is using to test out ML](https://breakingdefense.com/2023/01/inside-the-special-f-16-the-air-force-is-using-to-test-out-ML/)
- [AFRL, AFTC collaborate on future technology via weeklong autonomy summit](https://www.wpafb.af.mil/News/Article-Display/Article/3244878/afrl-aftc-collaborate-on-future-technology-via-weeklong-autonomy-summit/)
- [Demonstrating and testing machine learning applications in aerospace](https://aerospaceamerica.aiaa.org/year-in-review/demonstrating-and-testing-artificial-intelligence-applications-in-aerospace/)
## 1.2. Documentation
Documentation for the CoRL repository can be accessed directly as files in this repository, as a public documentation site, or can be built locally as an MkDocs site.
### 1.2.1. Guides
- [Quick Start Guide](guides/quick-start-guide.md)
### 1.2.2. Documentation Web Site
The [full public documentation site](https://act3-ace.github.io/CoRL/) is available on GitHub pages.
### 1.2.3. Local Documentation
A local version of the documentation site can be built using [MkDocs](https://www.mkdocs.org/).
Build the documentation:
```sh
mkdocs build
```
> Follow CLI prompts, as needed, to install all required plugins.
Serve the documentation:
```sh
mkdocs serve
```
## 1.3. Notices and Warnings
### 1.3.1. Initial Contributors
Initial contributors include scientists and engineers associated with the [Air Force Research Laboratory (AFRL)](https://www.afrl.af.mil/), [Autonomy Capability Team 3 (ACT3)](https://www.afrl.af.mil/ACT3/), and the [Aerospace Systems Directorate (RQ)](https://www.afrl.af.mil/RQ/).
### 1.3.2. Citing CoRL
If you use CoRL in your work, please use the following BibTeX to cite the CoRL white paper:
```bibtex
@inproceedings{
title={CoRL: Environment Creation and Management Focused on System Integration},
author={Justin D. Merrick, Benjamin K. Heiner, Cameron Long, Brian Stieber, Steve Fierro, Vardaan Gangal, Madison Blake, Joshua Blackburn},
year={2023},
url={https://arxiv.org/abs/2303.02182}
}
```
To cite the source code, use the **Cite this repository** option on GitHub to access the reference.
### 1.3.3. Distribution Statement
Approved for public release: distribution unlimited.
#### 1.3.3.1. Case Number
| Date | Release Number | Description |
| :--------: | :--------------------: | :--------------: |
| 2022-05-20 | AFRL-2022-2455 | Initial release |
| 2023-03-02 | APRS-RYZ-2023-01-00006 | Second release |
| 2024-21-03 | AFRL-2024-1562 | Third release |
#### 1.3.3.2. Designation Indicator
- Controlled by: Air Force Research Laboratory (AFRL)
- Controlled by: AFRL Autonomy Capability Team (ACT3)
#### 1.3.3.3. Points of Contact
- [Terry Wilson](mailto:terry.wilson.11@us.af.mil)
- [Benjamin Heiner](mailto:benjamin.heiner@us.af.mil)
- [Kerianne Hobbs](mailto:kerianne.hobbs@us.af.mil)
##### 1.3.3.3.1. Repository Contributors
{{ get_authors() }}
##### 1.3.3.3.2. Documentation Contributors
{{ git_site_authors }}
{{ include_glossary_abbreviations() }}
{{ include_bottom_banner() }}
Raw data
{
"_id": null,
"home_page": "https://github.com/act3-ace/CoRL",
"name": "corl",
"maintainer": "Benjamin K Heiner",
"docs_url": null,
"requires_python": "<3.12,>=3.10",
"maintainer_email": "benjamin.heiner@us.af.mil",
"keywords": "Deep, Reinforcement, Learning, CoRL, act3, ACT3",
"author": "Benjamin K Heiner",
"author_email": "benjamin.heiner@us.af.mil",
"download_url": "https://files.pythonhosted.org/packages/87/dd/83bb53081d0a1fdc58298b212f3f42f56b977a68e4dbf587d626d45ad0e5/corl-3.16.2.tar.gz",
"platform": null,
"description": "---\ntitle: CoRL\n---\n\n<!-- {{ include_top_banner() }} -->\n\n<!-- {{ include_github_badges() }} -->\n\n<!-- {{ include_repo_badges() }} -->\n\n# 1. Core ACT3 Reinforcement Learning Library\n\n> **This repository and corresponding documentation site are currently under construction. We are still porting items and updating instructions for GitHub.**\n\n## 1.1. Summary\n\nThe Core ACT3 Reinforcement Learning library (CoRL) is created and maintained by the Air Force Research Laboratory\u2019s (AFRL) [Autonomy Capability Team (ACT3)](https://www.afrl.af.mil/ACT3/). CoRL is intended to enable scalable deep reinforcement learning (RL) experimentation in a manner extensible to new simulations and new ways for the learning agents to interact with them. The objective is to make RL research easier by removing lock-in to particular simulations.\n\n### 1.1.1. Benefits\n\n- Makes RL environment development significantly easier\n- Provides hyper configurable environments, agents and experiments\n- Record observations by adding a few lines of config (instead of creating a new file for each observation)\n- Reuse glues/dones/rewards between different tasks if they are general\n- Uses an episode parameter provider (EPP) to randomize both domain and curriculum learning\n- Has an integration first focus, which means that integrating agents to the real world or different simulators is significantly easier\n\n### 1.1.2. Related Publications\n\n- [CoRL: Environment Creation and Management Focused on System Integration](https://arxiv.org/abs/2303.02182)\n- [Inside the special F-16 the Air Force is using to test out ML](https://breakingdefense.com/2023/01/inside-the-special-f-16-the-air-force-is-using-to-test-out-ML/)\n- [AFRL, AFTC collaborate on future technology via weeklong autonomy summit](https://www.wpafb.af.mil/News/Article-Display/Article/3244878/afrl-aftc-collaborate-on-future-technology-via-weeklong-autonomy-summit/)\n- [Demonstrating and testing machine learning applications in aerospace](https://aerospaceamerica.aiaa.org/year-in-review/demonstrating-and-testing-artificial-intelligence-applications-in-aerospace/)\n\n## 1.2. Documentation\n\nDocumentation for the CoRL repository can be accessed directly as files in this repository, as a public documentation site, or can be built locally as an MkDocs site.\n\n### 1.2.1. Guides\n\n- [Quick Start Guide](guides/quick-start-guide.md)\n\n### 1.2.2. Documentation Web Site\n\nThe [full public documentation site](https://act3-ace.github.io/CoRL/) is available on GitHub pages.\n\n### 1.2.3. Local Documentation\n\nA local version of the documentation site can be built using [MkDocs](https://www.mkdocs.org/).\n\nBuild the documentation:\n\n```sh\nmkdocs build\n```\n\n> Follow CLI prompts, as needed, to install all required plugins.\n\nServe the documentation:\n\n```sh\nmkdocs serve\n```\n\n## 1.3. Notices and Warnings\n\n### 1.3.1. Initial Contributors\n\nInitial contributors include scientists and engineers associated with the [Air Force Research Laboratory (AFRL)](https://www.afrl.af.mil/), [Autonomy Capability Team 3 (ACT3)](https://www.afrl.af.mil/ACT3/), and the [Aerospace Systems Directorate (RQ)](https://www.afrl.af.mil/RQ/).\n\n### 1.3.2. Citing CoRL\n\nIf you use CoRL in your work, please use the following BibTeX to cite the CoRL white paper:\n\n```bibtex\n@inproceedings{\n title={CoRL: Environment Creation and Management Focused on System Integration},\n author={Justin D. Merrick, Benjamin K. Heiner, Cameron Long, Brian Stieber, Steve Fierro, Vardaan Gangal, Madison Blake, Joshua Blackburn},\n year={2023},\n url={https://arxiv.org/abs/2303.02182}\n}\n```\n\nTo cite the source code, use the **Cite this repository** option on GitHub to access the reference.\n\n### 1.3.3. Distribution Statement\n\nApproved for public release: distribution unlimited.\n\n#### 1.3.3.1. Case Number\n\n| Date | Release Number | Description |\n| :--------: | :--------------------: | :--------------: |\n| 2022-05-20 | AFRL-2022-2455 | Initial release |\n| 2023-03-02 | APRS-RYZ-2023-01-00006 | Second release |\n| 2024-21-03 | AFRL-2024-1562 | Third release |\n\n#### 1.3.3.2. Designation Indicator\n\n- Controlled by: Air Force Research Laboratory (AFRL)\n- Controlled by: AFRL Autonomy Capability Team (ACT3)\n\n#### 1.3.3.3. Points of Contact\n\n- [Terry Wilson](mailto:terry.wilson.11@us.af.mil)\n- [Benjamin Heiner](mailto:benjamin.heiner@us.af.mil)\n- [Kerianne Hobbs](mailto:kerianne.hobbs@us.af.mil)\n\n##### 1.3.3.3.1. Repository Contributors\n\n{{ get_authors() }}\n\n##### 1.3.3.3.2. Documentation Contributors\n\n{{ git_site_authors }}\n\n{{ include_glossary_abbreviations() }}\n\n{{ include_bottom_banner() }}\n",
"bugtrack_url": null,
"license": null,
"summary": "Core ACT3 Reinforcement Learning (RL) Library - Core framework and base implementations of common things such as controllers, glues, observes, sensors, evaluation, and etc",
"version": "3.16.2",
"project_urls": {
"Documentation": "https://github.com/act3-ace/CoRL",
"Homepage": "https://github.com/act3-ace/CoRL",
"Repository": "https://github.com/act3-ace/CoRL"
},
"split_keywords": [
"deep",
" reinforcement",
" learning",
" corl",
" act3",
" act3"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ac4ba667a9136b70a176db969632fa0678a584bf5c349563123777d31c5bd1dc",
"md5": "52428b4de6a662154d7ac69adfa2e242",
"sha256": "06cb9a555821bd4630be466a3f4a3b992360405441a42b5bc7c45f85e03fd856"
},
"downloads": -1,
"filename": "corl-3.16.2-cp310-cp310-manylinux_2_35_x86_64.whl",
"has_sig": false,
"md5_digest": "52428b4de6a662154d7ac69adfa2e242",
"packagetype": "bdist_wheel",
"python_version": "cp310",
"requires_python": "<3.12,>=3.10",
"size": 538265,
"upload_time": "2024-04-12T14:29:52",
"upload_time_iso_8601": "2024-04-12T14:29:52.106195Z",
"url": "https://files.pythonhosted.org/packages/ac/4b/a667a9136b70a176db969632fa0678a584bf5c349563123777d31c5bd1dc/corl-3.16.2-cp310-cp310-manylinux_2_35_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "87dd83bb53081d0a1fdc58298b212f3f42f56b977a68e4dbf587d626d45ad0e5",
"md5": "fedceec979a6eb4627d9b3c6bffb8f77",
"sha256": "e99d21c6292e1b425f40b15ba34b9c8bdff82b9350ffcd27f52ea61b2c7647c7"
},
"downloads": -1,
"filename": "corl-3.16.2.tar.gz",
"has_sig": false,
"md5_digest": "fedceec979a6eb4627d9b3c6bffb8f77",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.12,>=3.10",
"size": 322649,
"upload_time": "2024-04-12T14:29:54",
"upload_time_iso_8601": "2024-04-12T14:29:54.135376Z",
"url": "https://files.pythonhosted.org/packages/87/dd/83bb53081d0a1fdc58298b212f3f42f56b977a68e4dbf587d626d45ad0e5/corl-3.16.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-12 14:29:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "act3-ace",
"github_project": "CoRL",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "corl"
}
JSON
