# LitRL
<table>
<tr>
<td>Compatibility</td>
<td>
<a href="https://pypi.python.org/pypi/litrl" target="_blank">
<img src="https://img.shields.io/pypi/pyversions/litrl?color=%2334D058" alt="Python">
</a>
<a href="https://pypi.python.org/pypi/litrl" target="_blank">
<img src="https://img.shields.io/pypi/v/litrl.svg?color=%2334D058" alt="Pypi">
</a>
<a href="https://pypi.python.org/pypi/litrl" target="_blank">
<img src="https://img.shields.io/badge/os-linux%20%7C%20macOS%20%7C%20windows-2334D058" alt="Pypi">
</a>
</td>
</tr>
<tr>
<td>CI</td>
<td>
<a href="https://github.com/c-gohlke/LitRL/actions/workflows/pytest.yaml" target="_blank">
<img
src="https://github.com/c-gohlke/LitRL/actions/workflows/pytest.yaml/badge.svg"
alt="pytest">
</a>
<a href="https://github.com/c-gohlke/LitRL/actions/workflows/lint.yaml" target="_blank">
<img
src="https://github.com/c-gohlke/LitRL/actions/workflows/lint.yaml/badge.svg"
alt="Lint">
</a>
<a href="https://codecov.io/gh/c-gohlke/LitRL" >
<img
src="https://codecov.io/gh/c-gohlke/LitRL/graph/badge.svg?token=NDPHZERUJJ"
alt=coverage/>
</a>
</td>
</tr>
<tr>
<td>Powered by</td>
<td>
<a href="https://github.com/Lightning-AI/lightning" target="_blank">
<img
src="https://img.shields.io/badge/-Lightning-792ee5?logo=pytorchlightning&logoColor=white"
alt="PyTorch Lightning">
</a>
<a href="https://github.com/pytorch/rl" target="_blank">
<img src="https://img.shields.io/badge/TorchRL-green" alt="TorchRL">
</a>
<a href="https://github.com/mlflow/mlflow" target="_blank">
<img
src="https://img.shields.io/badge/mlflow-%23d9ead3.svg?logo=mlflow&logoColor=blue"
alt="MLFlow">
</a>
<a href="https://github.com/facebookresearch/hydra" target="_blank">
<img src="https://img.shields.io/badge/Hydra-green" alt="Hydra">
</a>
</tr>
</tr>
<tr>
<td>Contributing</td>
<td>
<a href="https://litrl.readthedocs.io/en/latest/" target="_blank">
<img
src="https://img.shields.io/readthedocs/litrl?color=%2334D058"
alt="Docs">
</a>
<a href="https://pypi.python.org/pypi/litrl" target="_blank">
<img
src="https://img.shields.io/pypi/l/litrl.svg?color=%2334D058"
alt="License">
</a>
<a href="http://mypy-lang.org" target="_blank">
<img
src="http://www.mypy-lang.org/static/mypy_badge.svg"
alt="mypy">
</a>
<a href="https://github.com/psf/black" target="_blank">
<img
src="https://img.shields.io/badge/code%20style-black-000000.svg"
alt="black">
</a>
<a href="https://github.com/astral-sh/ruff" target="_blank">
<img
src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json"
alt="ruff">
</a>
</td>
</td>
</tr>
<tr>
<td>Try it out</td>
<td>
<a href="https://huggingface.co/c-gohlke/LitRL" target="_blank">
<img
src="https://img.shields.io/badge/%F0%9F%A4%97%20Models-Huggingface-F8D521"
alt="Models">
</a>
<a href="https://c-gohlke-litrl-demo.hf.space/folder/ConnectFour" target="_blank">
<img
src="https://img.shields.io/badge/%F0%9F%A4%97%20Demo-Huggingface-F8D521"
alt="Demo">
</a>
<a
href="https://githubtocolab.com/c-gohlke/LitRL/blob/main/notebooks/colab/train_lunar_sac.ipynb"
target="_blank">
<img
src="https://colab.research.google.com/assets/colab-badge.svg"
alt="Colab">
</a>
</td>
</tr>
</table>
LitRL is optimized for code readability and expandability. It also provides a structure
for Reinforcement Learning research.
## Get Started
```bash
pip install LitRL[torchrl]
```
TorchRL may not be found in PyPI depending on your Python version/OS. If that occurs,
you can download the package using:
```bash
bash scripts/install_torchrl
pip install LitRL
```
## Run demo locally
```bash
python demo/backend/run.py
```
In a separate terminal
```bash
npm install --prefix demo/frontend
npm run dev --prefix demo/frontend
```
## Getting Started Windows
[C++ build tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/)
## Acknowledgments
The code structure was influenced by implementations in:
- [CleanRL](https://github.com/vwxyzjn/cleanrl/tree/master)
- [Lizhi-sjtu](https://github.com/Lizhi-sjtu/DRL-code-pytorch)
- [lightning_bolts](https://github.com/Lightning-Universe/lightning-bolts/tree/master/src/pl_bolts/models/rl)
Specific algorithms were also influenced by:
- SAC: [Haarnooja SAC](https://github.com/haarnoja/sac)
- Online Decision Transformer: [ODT](https://github.com/facebookresearch/online-dt)
- AlphaGo/Zero/MuZero: [Muzero](https://github.com/werner-duvaud/muzero-general)
Raw data
{
"_id": null,
"home_page": "",
"name": "litrl",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "",
"keywords": "pytorch,reinforcement-learning,machine-learning,mypy,pytorch-lightning,huggingface,torchrl",
"author": "Clement Gohlke",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/58/f2/927a3c77ff6936e7202da84024669444063aa6a812d776c83734692fbfc9/litrl-0.0.24.tar.gz",
"platform": null,
"description": "# LitRL\n\n<table>\n <tr>\n <td>Compatibility</td>\n <td>\n <a href=\"https://pypi.python.org/pypi/litrl\" target=\"_blank\">\n <img src=\"https://img.shields.io/pypi/pyversions/litrl?color=%2334D058\" alt=\"Python\">\n </a>\n <a href=\"https://pypi.python.org/pypi/litrl\" target=\"_blank\">\n <img src=\"https://img.shields.io/pypi/v/litrl.svg?color=%2334D058\" alt=\"Pypi\">\n </a>\n <a href=\"https://pypi.python.org/pypi/litrl\" target=\"_blank\">\n <img src=\"https://img.shields.io/badge/os-linux%20%7C%20macOS%20%7C%20windows-2334D058\" alt=\"Pypi\">\n </a>\n </td>\n </tr>\n <tr>\n <td>CI</td>\n <td>\n <a href=\"https://github.com/c-gohlke/LitRL/actions/workflows/pytest.yaml\" target=\"_blank\">\n <img\n src=\"https://github.com/c-gohlke/LitRL/actions/workflows/pytest.yaml/badge.svg\"\n alt=\"pytest\">\n </a>\n <a href=\"https://github.com/c-gohlke/LitRL/actions/workflows/lint.yaml\" target=\"_blank\">\n <img\n src=\"https://github.com/c-gohlke/LitRL/actions/workflows/lint.yaml/badge.svg\"\n alt=\"Lint\">\n </a>\n <a href=\"https://codecov.io/gh/c-gohlke/LitRL\" >\n <img\n src=\"https://codecov.io/gh/c-gohlke/LitRL/graph/badge.svg?token=NDPHZERUJJ\"\n alt=coverage/>\n </a>\n </td>\n </tr>\n <tr>\n <td>Powered by</td>\n <td>\n <a href=\"https://github.com/Lightning-AI/lightning\" target=\"_blank\">\n <img\n src=\"https://img.shields.io/badge/-Lightning-792ee5?logo=pytorchlightning&logoColor=white\"\n alt=\"PyTorch Lightning\">\n </a>\n <a href=\"https://github.com/pytorch/rl\" target=\"_blank\">\n <img src=\"https://img.shields.io/badge/TorchRL-green\" alt=\"TorchRL\">\n </a>\n <a href=\"https://github.com/mlflow/mlflow\" target=\"_blank\">\n <img\n src=\"https://img.shields.io/badge/mlflow-%23d9ead3.svg?logo=mlflow&logoColor=blue\"\n alt=\"MLFlow\">\n </a>\n <a href=\"https://github.com/facebookresearch/hydra\" target=\"_blank\">\n <img src=\"https://img.shields.io/badge/Hydra-green\" alt=\"Hydra\">\n </a>\n </tr>\n </tr>\n <tr>\n <td>Contributing</td>\n <td>\n <a href=\"https://litrl.readthedocs.io/en/latest/\" target=\"_blank\">\n <img\n src=\"https://img.shields.io/readthedocs/litrl?color=%2334D058\"\n alt=\"Docs\">\n </a>\n <a href=\"https://pypi.python.org/pypi/litrl\" target=\"_blank\">\n <img\n src=\"https://img.shields.io/pypi/l/litrl.svg?color=%2334D058\"\n alt=\"License\">\n </a>\n <a href=\"http://mypy-lang.org\" target=\"_blank\">\n <img\n src=\"http://www.mypy-lang.org/static/mypy_badge.svg\"\n alt=\"mypy\">\n </a>\n <a href=\"https://github.com/psf/black\" target=\"_blank\">\n <img\n src=\"https://img.shields.io/badge/code%20style-black-000000.svg\"\n alt=\"black\">\n </a>\n <a href=\"https://github.com/astral-sh/ruff\" target=\"_blank\">\n <img\n src=\"https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json\"\n alt=\"ruff\">\n </a>\n </td>\n </td>\n </tr>\n <tr>\n <td>Try it out</td>\n <td>\n <a href=\"https://huggingface.co/c-gohlke/LitRL\" target=\"_blank\">\n <img\n src=\"https://img.shields.io/badge/%F0%9F%A4%97%20Models-Huggingface-F8D521\"\n alt=\"Models\">\n </a>\n <a href=\"https://c-gohlke-litrl-demo.hf.space/folder/ConnectFour\" target=\"_blank\">\n <img\n src=\"https://img.shields.io/badge/%F0%9F%A4%97%20Demo-Huggingface-F8D521\"\n alt=\"Demo\">\n </a>\n <a\n href=\"https://githubtocolab.com/c-gohlke/LitRL/blob/main/notebooks/colab/train_lunar_sac.ipynb\"\n target=\"_blank\">\n <img\n src=\"https://colab.research.google.com/assets/colab-badge.svg\"\n alt=\"Colab\">\n </a>\n </td>\n </tr>\n</table>\n\nLitRL is optimized for code readability and expandability. It also provides a structure\n\n for Reinforcement Learning research.\n\n## Get Started\n\n```bash\npip install LitRL[torchrl]\n```\n\nTorchRL may not be found in PyPI depending on your Python version/OS. If that occurs,\n you can download the package using:\n\n```bash\nbash scripts/install_torchrl\npip install LitRL\n```\n\n## Run demo locally\n\n```bash\npython demo/backend/run.py\n```\n\nIn a separate terminal\n\n```bash\nnpm install --prefix demo/frontend\nnpm run dev --prefix demo/frontend\n```\n\n## Getting Started Windows\n\n[C++ build tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/)\n\n## Acknowledgments\n\nThe code structure was influenced by implementations in:\n\n- [CleanRL](https://github.com/vwxyzjn/cleanrl/tree/master)\n- [Lizhi-sjtu](https://github.com/Lizhi-sjtu/DRL-code-pytorch)\n- [lightning_bolts](https://github.com/Lightning-Universe/lightning-bolts/tree/master/src/pl_bolts/models/rl)\n\nSpecific algorithms were also influenced by:\n\n- SAC: [Haarnooja SAC](https://github.com/haarnoja/sac)\n- Online Decision Transformer: [ODT](https://github.com/facebookresearch/online-dt)\n- AlphaGo/Zero/MuZero: [Muzero](https://github.com/werner-duvaud/muzero-general)\n",
"bugtrack_url": null,
"license": "",
"summary": "Implementation of RL algorithms in PyTorch Lightning",
"version": "0.0.24",
"project_urls": {
"Demo": "https://huggingface.co/spaces/c-gohlke/litrl-demo",
"Documentation": "https://litrl.readthedocs.io/en/latest/",
"Homepage": "https://github.com/c-gohlke/LightningRL",
"Repository": "https://github.com/c-gohlke/LightningRL"
},
"split_keywords": [
"pytorch",
"reinforcement-learning",
"machine-learning",
"mypy",
"pytorch-lightning",
"huggingface",
"torchrl"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f360a6fc43a8cc75685904ec4885a1c5e95172c0bdb845770cf9208180d149fd",
"md5": "66d1fd60348a9d33cef30e5afa4e2f6f",
"sha256": "d258bfca42da317b7d4b7cb235daa688c9048b59d5dea32b8ff6cabb8f64cf9a"
},
"downloads": -1,
"filename": "litrl-0.0.24-py3-none-any.whl",
"has_sig": false,
"md5_digest": "66d1fd60348a9d33cef30e5afa4e2f6f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 41516,
"upload_time": "2024-02-01T08:09:56",
"upload_time_iso_8601": "2024-02-01T08:09:56.522881Z",
"url": "https://files.pythonhosted.org/packages/f3/60/a6fc43a8cc75685904ec4885a1c5e95172c0bdb845770cf9208180d149fd/litrl-0.0.24-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "58f2927a3c77ff6936e7202da84024669444063aa6a812d776c83734692fbfc9",
"md5": "039ffe08b32ca98e3ff2b3e75712a396",
"sha256": "d031cd66365d8207188294d097e2146038b90fe4306746a9eaf083a9accea475"
},
"downloads": -1,
"filename": "litrl-0.0.24.tar.gz",
"has_sig": false,
"md5_digest": "039ffe08b32ca98e3ff2b3e75712a396",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 31008,
"upload_time": "2024-02-01T08:09:58",
"upload_time_iso_8601": "2024-02-01T08:09:58.350401Z",
"url": "https://files.pythonhosted.org/packages/58/f2/927a3c77ff6936e7202da84024669444063aa6a812d776c83734692fbfc9/litrl-0.0.24.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-01 08:09:58",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "c-gohlke",
"github_project": "LightningRL",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "litrl"
}
JSON
