torchdriveenv

Name	torchdriveenv JSON
Version	0.1.1 JSON
	download
home_page	None
Summary	TorchDriveEnv is a lightweight 2D driving reinforcement learning environment, supported by a solid simulator and smart non-playable characters
upload_time	2024-05-07 00:56:27
maintainer	None
docs_url	None
author	None
requires_python	>=3.8
license	None
keywords	reinforcement learning drive rl environment torch-drive-env torchdriveenv invertedai inverted ai
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # Installation

The basic installation of torchdriveenv uses an OpenCV renderer, which is slower but easy to install. PyTorch3D renderer can be faster, but it requires specific versions of CUDA and PyTorch, so it is best installed in Docker.

## Opencv rendering

To install the “torchdriveenv” with opencv rendering:
```
pip install torchdriveenv
```

To run examples:
Set the `$IAI_API_KEY` and `$WANDB_API_KEY`
```
pip install torchdriveenv[baselines]
cd examples
python rl_training.py
```

## Pytorch3d rendering

To install the “torchdriveenv” with Pytorch3d rendering:
```
docker build --target torchdriveenv-first-release -t torchdriveenv-first-release:latest .
```

To run examples:
Set the `$IAI_API_KEY` and `$WANDB_API_KEY`
```
cd examples
docker compose up rl-training
```

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "torchdriveenv",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3.8",
    "maintainer_email": null,
    "keywords": "reinforcement learning, drive, RL environment, torch-drive-env, torchdriveenv, invertedai, inverted ai",
    "author": null,
    "author_email": "\"Inverted AI Ltd.\" <info@inverted.ai>",
    "download_url": "https://files.pythonhosted.org/packages/18/14/30a006da240b3d7c1df1f349de2665d1d0ae39534ada7979dcc4a9430911/torchdriveenv-0.1.1.tar.gz",
    "platform": null,
    "description": "# Installation\n\nThe basic installation of torchdriveenv uses an OpenCV renderer, which is slower but easy to install. PyTorch3D renderer can be faster, but it requires specific versions of CUDA and PyTorch, so it is best installed in Docker.\n\n## Opencv rendering\n\nTo install the \u201ctorchdriveenv\u201d with opencv rendering:\n```\npip install torchdriveenv\n```\n\nTo run examples:\nSet the `$IAI_API_KEY` and `$WANDB_API_KEY`\n```\npip install torchdriveenv[baselines]\ncd examples\npython rl_training.py\n```\n\n## Pytorch3d rendering\n\nTo install the \u201ctorchdriveenv\u201d with Pytorch3d rendering:\n```\ndocker build --target torchdriveenv-first-release -t torchdriveenv-first-release:latest .\n```\n\nTo run examples:\nSet the `$IAI_API_KEY` and `$WANDB_API_KEY`\n```\ncd examples\ndocker compose up rl-training\n```\n",
    "bugtrack_url": null,
    "license": null,
    "summary": "TorchDriveEnv is a lightweight 2D driving reinforcement learning environment, supported by a solid simulator and smart non-playable characters",
    "version": "0.1.1",
    "project_urls": null,
    "split_keywords": [
        "reinforcement learning",
        " drive",
        " rl environment",
        " torch-drive-env",
        " torchdriveenv",
        " invertedai",
        " inverted ai"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "118c1c00f43c2e689704a85b1099859ef7b46c27c4b5a1a5d631f2c3c9992215",
                "md5": "9d66301f77f2ded27410f48968135587",
                "sha256": "19219d8ee5db11fa2a72630c0cf1ba439da4d14e76f0e6308566126846e21d8f"
            },
            "downloads": -1,
            "filename": "torchdriveenv-0.1.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "9d66301f77f2ded27410f48968135587",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.8",
            "size": 5805914,
            "upload_time": "2024-05-07T00:56:25",
            "upload_time_iso_8601": "2024-05-07T00:56:25.469505Z",
            "url": "https://files.pythonhosted.org/packages/11/8c/1c00f43c2e689704a85b1099859ef7b46c27c4b5a1a5d631f2c3c9992215/torchdriveenv-0.1.1-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "181430a006da240b3d7c1df1f349de2665d1d0ae39534ada7979dcc4a9430911",
                "md5": "86831c53c458f9c3cb47fd66e602efc3",
                "sha256": "ea00be0e073e479320a5ecaea4908851ab1686942c7d7a04ff0c6c00b5c19058"
            },
            "downloads": -1,
            "filename": "torchdriveenv-0.1.1.tar.gz",
            "has_sig": false,
            "md5_digest": "86831c53c458f9c3cb47fd66e602efc3",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.8",
            "size": 5725259,
            "upload_time": "2024-05-07T00:56:27",
            "upload_time_iso_8601": "2024-05-07T00:56:27.799143Z",
            "url": "https://files.pythonhosted.org/packages/18/14/30a006da240b3d7c1df1f349de2665d1d0ae39534ada7979dcc4a9430911/torchdriveenv-0.1.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-05-07 00:56:27",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "torchdriveenv"
}