# Fragile
[](https://fragile.readthedocs.io/en/latest/?badge=latest)
[](https://codecov.io/github/FragileTech/fragile)
[](https://pypi.org/project/fragile/)
[](https://hub.docker.com/r/fragiletech/fragile/tags)
[](https://github.com/ambv/black)
[](https://opensource.org/licenses/MIT)
Fragile is a framework for developing optimization algorithms inspired by Fractal AI and running them at scale.
## Features
- Provides classes and an API for easily developing planning algorithms
- Provides an classes and an API for function optimization
- Build in visualizations of the sampling process
- Fully documented and tested (In progress)
- Support for parallelization and distributed search processes (In progress)
## About FractalAI
FractalAI is based on the framework of [non-equilibrium thermodynamics](https://en.wikipedia.org/wiki/Non-equilibrium_thermodynamics), and can be used to derive new mathematical tools for efficiently exploring state spaces.
The principles of our work are accessible online:
- [Arxiv](https://arxiv.org/abs/1803.05049) manuscript describing the fundamental principles of our work.
- [Blog](http://entropicai.blogspot.com) that describes our early research process.
- [Youtube channel](https://www.youtube.com/user/finaysergio/videos) with videos showing how different prototypes work.
- [GitHub repository](https://github.com/FragileTech/FractalAI) containing a prototype that solves most Atari games.
## Getting started
Check out the [getting started](https://fragile.readthedocs.io/en/latest/resources/examples/01_getting_started.html)
section of the docs, or the [examples](https://github.com/FragileTech/fragile/tree/master/examples) folder.
## Running in docker
The fragile docker container will execute a Jupyter notebook accessible on port 8080 with password: `fragile`
You can pull a docker image from Docker Hub running:
```bash
docker pull fragiletech/fragile:version-tag
```
Where version-tag corresponds to the fragile version that will be installed in the pulled image.
## Installation
This framework has been tested in Ubuntu 18.04 and supports Python 3.8 and 3.9.
If you find any problems running it in a different OS or Python version please open an issue.
It can be installed with `pip install fragile["all"]`.
You can find the pinned versions of the minimum requirements to install the core module in `requirements.txt`,
and the pinned versions of all the optional requirements in `requirements-all.txt`.
Detailed installation instructions can be found in the [docs](https://fragile.readthedocs.io/en/latest/resources/installation.html).
## Documentation
You can access the documentation on [Read The Docs](https://fragile.readthedocs.io/en/latest/).
## Roadmap
Upcoming features: _(not necessarily in order)_
- Fix documentation and add examples for the `distributed` module
- Upload Montezuma solver
- Add new algorithms to sample different state spaces.
- Add a benchmarking module
- Add deep learning API
## Contributing
Contribution are welcome. Please take a look at [contributining](docsrc/markdown/CONTRIBUTING.md)
and respect the [code of conduct](docsrc/markdown/CODE_OF_CONDUCT.md).
## Cite us
If you use this framework in your research please cite us as:
@misc{1803.05049,
Author = {Sergio Hernández Cerezo and Guillem Duran Ballester},
Title = {Fractal AI: A fragile theory of intelligence},
Year = {2018},
Eprint = {arXiv:1803.05049},
}
## License
This project is MIT licensed. See `LICENSE.md` for the complete text.
Raw data
{
"_id": null,
"home_page": "https://github.com/FragileTech/fragile",
"name": "fragile",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "reinforcement learning,artificial intelligence,monte carlo,planning",
"author": "Guillem Duran Ballester",
"author_email": "info@fragile.tech",
"download_url": "https://files.pythonhosted.org/packages/e2/9e/6cd4a50fa02ab11829c6159bfaa9307b9bd919ad31f0400c90914b43126c/fragile-0.0.60.tar.gz",
"platform": null,
"description": "# Fragile\n\n[](https://fragile.readthedocs.io/en/latest/?badge=latest)\n[](https://codecov.io/github/FragileTech/fragile)\n[](https://pypi.org/project/fragile/)\n[](https://hub.docker.com/r/fragiletech/fragile/tags)\n[](https://github.com/ambv/black)\n[](https://opensource.org/licenses/MIT)\n\nFragile is a framework for developing optimization algorithms inspired by Fractal AI and running them at scale.\n\n## Features\n\n- Provides classes and an API for easily developing planning algorithms\n- Provides an classes and an API for function optimization\n- Build in visualizations of the sampling process\n- Fully documented and tested (In progress)\n- Support for parallelization and distributed search processes (In progress)\n\n## About FractalAI\n\nFractalAI is based on the framework of [non-equilibrium thermodynamics](https://en.wikipedia.org/wiki/Non-equilibrium_thermodynamics), and can be used to derive new mathematical tools for efficiently exploring state spaces.\n \nThe principles of our work are accessible online:\n\n- [Arxiv](https://arxiv.org/abs/1803.05049) manuscript describing the fundamental principles of our work.\n- [Blog](http://entropicai.blogspot.com) that describes our early research process.\n- [Youtube channel](https://www.youtube.com/user/finaysergio/videos) with videos showing how different prototypes work.\n- [GitHub repository](https://github.com/FragileTech/FractalAI) containing a prototype that solves most Atari games.\n\n## Getting started\n\nCheck out the [getting started](https://fragile.readthedocs.io/en/latest/resources/examples/01_getting_started.html) \nsection of the docs, or the [examples](https://github.com/FragileTech/fragile/tree/master/examples) folder.\n\n## Running in docker\n\nThe fragile docker container will execute a Jupyter notebook accessible on port 8080 with password: `fragile`\n\nYou can pull a docker image from Docker Hub running:\n\n```bash\n docker pull fragiletech/fragile:version-tag\n```\n\nWhere version-tag corresponds to the fragile version that will be installed in the pulled image.\n\n## Installation\n\nThis framework has been tested in Ubuntu 18.04 and supports Python 3.8 and 3.9.\nIf you find any problems running it in a different OS or Python version please open an issue.\n\nIt can be installed with `pip install fragile[\"all\"]`.\n\nYou can find the pinned versions of the minimum requirements to install the core module in `requirements.txt`,\nand the pinned versions of all the optional requirements in `requirements-all.txt`.\n\nDetailed installation instructions can be found in the [docs](https://fragile.readthedocs.io/en/latest/resources/installation.html).\n\n## Documentation\n\nYou can access the documentation on [Read The Docs](https://fragile.readthedocs.io/en/latest/).\n \n## Roadmap\n\nUpcoming features: _(not necessarily in order)_\n- Fix documentation and add examples for the `distributed` module\n- Upload Montezuma solver\n- Add new algorithms to sample different state spaces.\n- Add a benchmarking module\n- Add deep learning API\n\n## Contributing\n\nContribution are welcome. Please take a look at [contributining](docsrc/markdown/CONTRIBUTING.md) \nand respect the [code of conduct](docsrc/markdown/CODE_OF_CONDUCT.md).\n \n## Cite us\nIf you use this framework in your research please cite us as:\n\n @misc{1803.05049,\n Author = {Sergio Hern\u00e1ndez Cerezo and Guillem Duran Ballester},\n Title = {Fractal AI: A fragile theory of intelligence},\n Year = {2018},\n Eprint = {arXiv:1803.05049},\n }\n \n## License\n\nThis project is MIT licensed. See `LICENSE.md` for the complete text.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Framework for developing FractalAI based algorithms.",
"version": "0.0.60",
"project_urls": {
"Download": "https://github.com/FragileTech/fragile",
"Homepage": "https://github.com/FragileTech/fragile"
},
"split_keywords": [
"reinforcement learning",
"artificial intelligence",
"monte carlo",
"planning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9d820e4320c266d779192ff6b56c9d14b9e885a03dc0acb37efff98a7058fc3a",
"md5": "10f4c3da4a4f33dcb838bbe816ff2522",
"sha256": "b89ec56abf8f707498fe0a7f3f7b9c815963e6b463f39dfe3107e82f98d668c5"
},
"downloads": -1,
"filename": "fragile-0.0.60-py3-none-any.whl",
"has_sig": false,
"md5_digest": "10f4c3da4a4f33dcb838bbe816ff2522",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 90107,
"upload_time": "2023-10-09T10:03:29",
"upload_time_iso_8601": "2023-10-09T10:03:29.592419Z",
"url": "https://files.pythonhosted.org/packages/9d/82/0e4320c266d779192ff6b56c9d14b9e885a03dc0acb37efff98a7058fc3a/fragile-0.0.60-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "e29e6cd4a50fa02ab11829c6159bfaa9307b9bd919ad31f0400c90914b43126c",
"md5": "5d61690b2489163bed395291e0a65936",
"sha256": "425b6cca59caca85322884b1da38c2928ed822097d65ffde25774b78e14edbdd"
},
"downloads": -1,
"filename": "fragile-0.0.60.tar.gz",
"has_sig": false,
"md5_digest": "5d61690b2489163bed395291e0a65936",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 77940,
"upload_time": "2023-10-09T10:03:31",
"upload_time_iso_8601": "2023-10-09T10:03:31.164003Z",
"url": "https://files.pythonhosted.org/packages/e2/9e/6cd4a50fa02ab11829c6159bfaa9307b9bd919ad31f0400c90914b43126c/fragile-0.0.60.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-10-09 10:03:31",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "FragileTech",
"github_project": "fragile",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "fragile"
}
JSON
