| Name | regelum-control JSON |
| Version |
0.3.3
JSON |
| download |
| home_page | None |
| Summary | Regelum is a flexibly configurable framework for agent-environment simulation with a menu of predictive and reinforcement learning pipelines. |
| upload_time | 2024-10-20 19:33:09 |
| maintainer | None |
| docs_url | None |
| author | Georgiy Malaniya |
| requires_python | <4.0,>=3.9 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# About
`Regelum-control` stands as a framework designed to address optimal control and reinforcement learning (RL) tasks within continuous-time dynamical systems. It is made for researchers and engineers in reinforcement learning and control theory.
A detailed documentation is available [here](https://regelum.aidynamic.group/).
Explore [regelum-playground repo](https://github.com/osinenkop/regelum-playground) with ready-to-use examples.
# Features
- __Run pre-configured regelum algorithms with ease__. Regelum offers a set of implemented, ready-to-use algorithms in the domain of RL and Optimal Control.
It provides flexibility through multiple optimization backends, including CasADi and PyTorch, to accommodate various computational needs.
- __Stabilize your dynamical system with Regelum__. Regelum stands as a framework
designed to address optimal control and reinforcement learning (RL)
tasks within continuous-time dynamical systems.
It comes equipped with an array of default systems,
alongside a detailed tutorial that provides clear instructions
for users to instantiate their own environments.
- __Manage your experiment data__. Regelum seamlessly captures
every detail of your experiment with little to no configuration required.
From parameters to performance metrics, every datum is recorded. Through integration with [MLflow](https://mlflow.org/),
Regelum streamlines tracking, comparison and real-time monitoring of metrics.
- __Reproduce your experiments with ease__. Commit hashes and diffs for every experiment are also stored in Regelum,
offering the ability to reproduce your experiments at any time with simple terminal commands.
- __Configure your experiments efficiently__. Our [Hydra](https://hydra.cc/) fork within Regelum introduces enhanced functionaly,
making the configuration of your RL and Optimal Control tasks more accessible and user-friendly.
- __Fine-tune your models to perfection__ and achieve peak performance with minimal effort.
By integrating with Hydra, regelum inherently adopts Hydra's powerful hyperparameter tuning capability.
# Install regelum-control with pip
```bash
pip install regelum-control
```
# Developer setup
1. Clone the repository.
2. Run:
```bash
pip install -e .
bash scripts/developer-setup.sh
```
3. Check `requirements-dev.txt` in the root of the repo for additional details.
# Licence
This project is licensed under the terms of the [MIT license](./LICENSE).
## Bibtex reference
```
@misc{regelum2024,
author = {Pavel Osinenko, Grigory Yaremenko, Georgiy Malaniya, Anton Bolychev},
title = {Regelum: a framework for simulation, control and reinforcement learning},
howpublished = {\url{https://github.com/osinekop/regelum-control}},
year = {2024},
note = {Licensed under the MIT License}
}
```
Raw data
{
"_id": null,
"home_page": null,
"name": "regelum-control",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": "Georgiy Malaniya",
"author_email": "pwlsd.gm@gmail.com> Anton Bolychev <bolychev.anton@gmail.com> Grigoriy Yaremenko <yaremenko8@gmail.com> Pavel Osinenko <p.osinenko@yandex.ru",
"download_url": "https://files.pythonhosted.org/packages/2c/1a/4b15742eea6f7e4aec69d97df0a692b77c0865b2552819dc30630f52b878/regelum_control-0.3.3.tar.gz",
"platform": null,
"description": "\n\n# About\n\n`Regelum-control` stands as a framework designed to address optimal control and reinforcement learning (RL) tasks within continuous-time dynamical systems. It is made for researchers and engineers in reinforcement learning and control theory.\n\nA detailed documentation is available [here](https://regelum.aidynamic.group/).\n\nExplore [regelum-playground repo](https://github.com/osinenkop/regelum-playground) with ready-to-use examples.\n\n# Features\n\n- __Run pre-configured regelum algorithms with ease__. Regelum offers a set of implemented, ready-to-use algorithms in the domain of RL and Optimal Control. \nIt provides flexibility through multiple optimization backends, including CasADi and PyTorch, to accommodate various computational needs.\n\n- __Stabilize your dynamical system with Regelum__. Regelum stands as a framework \ndesigned to address optimal control and reinforcement learning (RL) \ntasks within continuous-time dynamical systems. \nIt comes equipped with an array of default systems, \nalongside a detailed tutorial that provides clear instructions \nfor users to instantiate their own environments.\n\n- __Manage your experiment data__. Regelum seamlessly captures\nevery detail of your experiment with little to no configuration required. \nFrom parameters to performance metrics, every datum is recorded. Through integration with [MLflow](https://mlflow.org/), \nRegelum streamlines tracking, comparison and real-time monitoring of metrics.\n\n- __Reproduce your experiments with ease__. Commit hashes and diffs for every experiment are also stored in Regelum, \noffering the ability to reproduce your experiments at any time with simple terminal commands.\n\n- __Configure your experiments efficiently__. Our [Hydra](https://hydra.cc/) fork within Regelum introduces enhanced functionaly, \nmaking the configuration of your RL and Optimal Control tasks more accessible and user-friendly.\n\n- __Fine-tune your models to perfection__ and achieve peak performance with minimal effort. \nBy integrating with Hydra, regelum inherently adopts Hydra's powerful hyperparameter tuning capability.\n\n# Install regelum-control with pip\n\n```bash\npip install regelum-control\n```\n\n# Developer setup\n\n1. Clone the repository.\n2. Run:\n ```bash\n pip install -e .\n bash scripts/developer-setup.sh\n ```\n3. Check `requirements-dev.txt` in the root of the repo for additional details.\n\n\n# Licence\n\nThis project is licensed under the terms of the [MIT license](./LICENSE).\n\n## Bibtex reference\n\n```\n@misc{regelum2024,\nauthor = {Pavel Osinenko, Grigory Yaremenko, Georgiy Malaniya, Anton Bolychev},\ntitle = {Regelum: a framework for simulation, control and reinforcement learning},\nhowpublished = {\\url{https://github.com/osinekop/regelum-control}},\nyear = {2024},\nnote = {Licensed under the MIT License}\n}\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Regelum is a flexibly configurable framework for agent-environment simulation with a menu of predictive and reinforcement learning pipelines.",
"version": "0.3.3",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "b0875268ba5a4a34d6d16ce749d07511244646fcd98151605967372e4c480d4d",
"md5": "7419aef47b3318a026a71b37b7b8ae67",
"sha256": "bebe93fb92acade966fea94da94c27f6c16469a36697b2887740b32a36109048"
},
"downloads": -1,
"filename": "regelum_control-0.3.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7419aef47b3318a026a71b37b7b8ae67",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 148136,
"upload_time": "2024-10-20T19:33:07",
"upload_time_iso_8601": "2024-10-20T19:33:07.521807Z",
"url": "https://files.pythonhosted.org/packages/b0/87/5268ba5a4a34d6d16ce749d07511244646fcd98151605967372e4c480d4d/regelum_control-0.3.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "2c1a4b15742eea6f7e4aec69d97df0a692b77c0865b2552819dc30630f52b878",
"md5": "69c40c89eddb7399852ea4b3f374dd03",
"sha256": "e85fe66c1fa7736e296b93ed094701041b47baead9a7fc1ea0be8cdb83458ffc"
},
"downloads": -1,
"filename": "regelum_control-0.3.3.tar.gz",
"has_sig": false,
"md5_digest": "69c40c89eddb7399852ea4b3f374dd03",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 135044,
"upload_time": "2024-10-20T19:33:09",
"upload_time_iso_8601": "2024-10-20T19:33:09.799821Z",
"url": "https://files.pythonhosted.org/packages/2c/1a/4b15742eea6f7e4aec69d97df0a692b77c0865b2552819dc30630f52b878/regelum_control-0.3.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-20 19:33:09",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "regelum-control"
}
