<div align="center">
<img src="docs/_static/images/moss.jpg" width="65%">
</div>
# Moss: A Python library for Reinforcement Learning
[](https://pypi.org/project/moss-rl/)
[](https://pypi.org/project/moss-rl/)
[](https://github.com/hilanzy/moss/blob/master/LICENSE)
**Moss** is a Python library for Reinforcement Learning based on [jax](https://github.com/google/jax).
## Installation
To get up and running quickly just follow the steps below:
**Installing from PyPI**: Moss is currently hosted on [PyPI](https://pypi.org/project/moss-rl/),
you can simply install Moss from PyPI with the following command:
```bash
pip install moss-rl
```
**Installing from github**: If you are interested in running Moss as a developer,
you can do so by cloning the Moss GitHub repository and then executing following command
from the main directory (where `setup.py` is located):
```bash
pip install -e ".[dev]"
```
After installation, open your python console and type
```python
import moss
print(moss.__version__)
```
If no error occurs, you have successfully installed Moss.
**Work on GPU or TPU**
If you want to run Moss with NVIDIA GPU, please run the steps below:
```bash
pip install --upgrade pip
# CUDA 12 installation
# Note: wheels only available on linux.
pip install --upgrade "jax[cuda12_pip]==0.4.9" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
# CUDA 11 installation
# Note: wheels only available on linux.
pip install --upgrade "jax[cuda11_pip]==0.4.9" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
```
Or if you want to run with Google Cloud TPU:
```bash
pip install "jax[tpu]==0.4.9" -f https://storage.googleapis.com/jax-releases/libtpu_releases.html
```
For more details, please see the JAX installation instructions [here](https://github.com/google/jax/tree/jax-v0.4.9#installation).
## Quick Start
This is an example of Impala to train Atari game(use [envpool](https://github.com/sail-sg/envpool)).
```bash
python examples/atari/impala.py --task_id Pong-v5 --learning_rate 1e-3
```
Raw data
{
"_id": null,
"home_page": "https://github.com/hilanzy/moss",
"name": "moss-rl",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "",
"keywords": "reinforcement-learning python machine learning",
"author": "lanzhiyi",
"author_email": "lanzhiy.mail@qq.com",
"download_url": "https://files.pythonhosted.org/packages/03/7e/903e06f50ea8bf84f8a27d11c779f41a517910a477d77bc1e982031344cf/moss-rl-0.0.5.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n <img src=\"docs/_static/images/moss.jpg\" width=\"65%\">\n</div>\n\n# Moss: A Python library for Reinforcement Learning\n\n[](https://pypi.org/project/moss-rl/)\n[](https://pypi.org/project/moss-rl/)\n[](https://github.com/hilanzy/moss/blob/master/LICENSE)\n\n**Moss** is a Python library for Reinforcement Learning based on [jax](https://github.com/google/jax).\n\n## Installation\n\nTo get up and running quickly just follow the steps below:\n\n **Installing from PyPI**: Moss is currently hosted on [PyPI](https://pypi.org/project/moss-rl/),\n you can simply install Moss from PyPI with the following command:\n\n ```bash\n pip install moss-rl\n ```\n\n **Installing from github**: If you are interested in running Moss as a developer,\n you can do so by cloning the Moss GitHub repository and then executing following command\n from the main directory (where `setup.py` is located):\n\n ```bash\n pip install -e \".[dev]\"\n ```\n\nAfter installation, open your python console and type\n\n ```python\n import moss\n print(moss.__version__)\n ```\n\nIf no error occurs, you have successfully installed Moss.\n\n**Work on GPU or TPU**\n\nIf you want to run Moss with NVIDIA GPU, please run the steps below:\n\n ```bash\n pip install --upgrade pip\n\n # CUDA 12 installation\n # Note: wheels only available on linux.\n pip install --upgrade \"jax[cuda12_pip]==0.4.9\" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html\n\n # CUDA 11 installation\n # Note: wheels only available on linux.\n pip install --upgrade \"jax[cuda11_pip]==0.4.9\" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html\n ```\n\nOr if you want to run with Google Cloud TPU:\n\n ```bash\n pip install \"jax[tpu]==0.4.9\" -f https://storage.googleapis.com/jax-releases/libtpu_releases.html\n ```\n\nFor more details, please see the JAX installation instructions [here](https://github.com/google/jax/tree/jax-v0.4.9#installation).\n\n## Quick Start\n\nThis is an example of Impala to train Atari game(use [envpool](https://github.com/sail-sg/envpool)).\n ```bash\n python examples/atari/impala.py --task_id Pong-v5 --learning_rate 1e-3\n ```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A Python library for Reinforcement Learning.",
"version": "0.0.5",
"project_urls": {
"Homepage": "https://github.com/hilanzy/moss"
},
"split_keywords": [
"reinforcement-learning",
"python",
"machine",
"learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "950f8872fc1363d743b11f341c3a311ea75870b971c8d62dcf5428ed37acc9c8",
"md5": "55e9c24c373dd7b633f606369bb92fc0",
"sha256": "45e67551eb0ae9b12de11a80161cb080d05da21acd5dc7a409edb2ecc60d06e8"
},
"downloads": -1,
"filename": "moss_rl-0.0.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "55e9c24c373dd7b633f606369bb92fc0",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 83866,
"upload_time": "2024-01-01T06:02:49",
"upload_time_iso_8601": "2024-01-01T06:02:49.254180Z",
"url": "https://files.pythonhosted.org/packages/95/0f/8872fc1363d743b11f341c3a311ea75870b971c8d62dcf5428ed37acc9c8/moss_rl-0.0.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "037e903e06f50ea8bf84f8a27d11c779f41a517910a477d77bc1e982031344cf",
"md5": "81a7cca2cecf1477faac706520b43ef7",
"sha256": "a27eaf71ba3bc0a3d539b277d9dfba7dcb716ce54b1973edf8d3071afaa63442"
},
"downloads": -1,
"filename": "moss-rl-0.0.5.tar.gz",
"has_sig": false,
"md5_digest": "81a7cca2cecf1477faac706520b43ef7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 47167,
"upload_time": "2024-01-01T06:02:54",
"upload_time_iso_8601": "2024-01-01T06:02:54.677530Z",
"url": "https://files.pythonhosted.org/packages/03/7e/903e06f50ea8bf84f8a27d11c779f41a517910a477d77bc1e982031344cf/moss-rl-0.0.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-01-01 06:02:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "hilanzy",
"github_project": "moss",
"github_not_found": true,
"lcname": "moss-rl"
}
JSON
