# Xenoverse: Toward Training General-Purpose Learning Agents (GLA) with Randomized Worlds
## xenoverse instead of a single universe
The recent research indicates that the generalization ability of learning agents is primarily dependent on the diversity of training environments. However, the real-world poses a significant limitation on the diversity itself, e.g., physical laws, the gravitational constant is almost constant. We believe this limitation is serious bottleneck to incentivize artificial general intelligence (AGI).
Xenoverse is a collection of extremely diverse worlds by procedural generation based on completely random parameters. We propose that AGI should not be trained and adapted in a single universe, but in xenoverse.
## collection of xenoverse environments
- [AnyMDP](xenoverse/anymdp): Procedurally generated unlimited general-purpose Markov Decision Processes (MDP) in discrete spaces.
- [AnyHVAC](xenoverse/anyhvac): Procedurally generated random room and equipments for Heating, Ventilation, and Air Conditioning (HVAC) control
- [MetaLanguage](xenoverse/metalang): Pseudo-language generated from randomized neural networks, benchmarking in-context language learning (ICLL).
- [MazeWorld](xenoverse/mazeworld): Procedurally generated immersed 3D mazes with diverse maze structures.
- [MazeControl](xenoverse/metcontrol): Randomized environments for classic control and locomotions.
# Installation
```bash
pip install xenoverse
```
# Reference
Related works
```bibtex
@article{wang2024benchmarking,
title={Benchmarking General Purpose In-Context Learning},
author={Wang, Fan and Lin, Chuan and Cao, Yang and Kang, Yu},
journal={arXiv preprint arXiv:2405.17234},
year={2024}
}
@article{wang2025towards,
title={Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds},
author={Wang, Fan and Shao, Pengtao and Zhang, Yiming and Yu, Bo and Liu, Shaoshan and Ding, Ning and Cao, Yang and Kang, Yu and Wang, Haifeng},
journal={arXiv preprint arXiv:2502.02869},
year={2025}
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/FutureAGI/xenoverse",
"name": "xenoverse",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": null,
"author": "WorldEditors",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/6f/d5/b5d8684790c56710c46aac22000f7c6e2bc75711eb371e0aac3125b53bb4/xenoverse-0.1.8.tar.gz",
"platform": null,
"description": "# Xenoverse: Toward Training General-Purpose Learning Agents (GLA) with Randomized Worlds\r\n\r\n## xenoverse instead of a single universe\r\n\r\nThe recent research indicates that the generalization ability of learning agents is primarily dependent on the diversity of training environments. However, the real-world poses a significant limitation on the diversity itself, e.g., physical laws, the gravitational constant is almost constant. We believe this limitation is serious bottleneck to incentivize artificial general intelligence (AGI).\r\n\r\nXenoverse is a collection of extremely diverse worlds by procedural generation based on completely random parameters. We propose that AGI should not be trained and adapted in a single universe, but in xenoverse.\r\n\r\n## collection of xenoverse environments\r\n\r\n- [AnyMDP](xenoverse/anymdp): Procedurally generated unlimited general-purpose Markov Decision Processes (MDP) in discrete spaces.\r\n\r\n- [AnyHVAC](xenoverse/anyhvac): Procedurally generated random room and equipments for Heating, Ventilation, and Air Conditioning (HVAC) control\r\n\r\n- [MetaLanguage](xenoverse/metalang): Pseudo-language generated from randomized neural networks, benchmarking in-context language learning (ICLL).\r\n\r\n- [MazeWorld](xenoverse/mazeworld): Procedurally generated immersed 3D mazes with diverse maze structures.\r\n\r\n- [MazeControl](xenoverse/metcontrol): Randomized environments for classic control and locomotions.\r\n\r\n\r\n# Installation\r\n\r\n```bash\r\npip install xenoverse\r\n```\r\n\r\n# Reference\r\nRelated works\r\n```bibtex\r\n@article{wang2024benchmarking,\r\n title={Benchmarking General Purpose In-Context Learning},\r\n author={Wang, Fan and Lin, Chuan and Cao, Yang and Kang, Yu},\r\n journal={arXiv preprint arXiv:2405.17234},\r\n year={2024}\r\n}\r\n@article{wang2025towards,\r\n title={Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds},\r\n author={Wang, Fan and Shao, Pengtao and Zhang, Yiming and Yu, Bo and Liu, Shaoshan and Ding, Ning and Cao, Yang and Kang, Yu and Wang, Haifeng},\r\n journal={arXiv preprint arXiv:2502.02869},\r\n year={2025}\r\n}\r\n```\r\n",
"bugtrack_url": null,
"license": "Apache",
"summary": "Collection of xeno-world environments for meta-training of general-purpose learning agents (GLAs)",
"version": "0.1.8",
"project_urls": {
"Homepage": "https://github.com/FutureAGI/xenoverse"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "237755222915559bf6304dfed5cb1dbb8043cafb78abae5a4da62599ee6580aa",
"md5": "413c3bb680b80d2380a146f9a613f675",
"sha256": "a62c449b8f9f4156f07e3fbce400eb7234816b3744a0ddf994ab2bc788c88ecc"
},
"downloads": -1,
"filename": "xenoverse-0.1.8-py3-none-any.whl",
"has_sig": false,
"md5_digest": "413c3bb680b80d2380a146f9a613f675",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 1345163,
"upload_time": "2025-08-18T07:50:45",
"upload_time_iso_8601": "2025-08-18T07:50:45.863781Z",
"url": "https://files.pythonhosted.org/packages/23/77/55222915559bf6304dfed5cb1dbb8043cafb78abae5a4da62599ee6580aa/xenoverse-0.1.8-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "6fd5b5d8684790c56710c46aac22000f7c6e2bc75711eb371e0aac3125b53bb4",
"md5": "86d6d86684a644cab160e5da0ef42bea",
"sha256": "795e0cdcf83a4c79b7923cc2464a76b5e3232793e920911220509e00c54653c4"
},
"downloads": -1,
"filename": "xenoverse-0.1.8.tar.gz",
"has_sig": false,
"md5_digest": "86d6d86684a644cab160e5da0ef42bea",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 1277882,
"upload_time": "2025-08-18T07:50:48",
"upload_time_iso_8601": "2025-08-18T07:50:48.204282Z",
"url": "https://files.pythonhosted.org/packages/6f/d5/b5d8684790c56710c46aac22000f7c6e2bc75711eb371e0aac3125b53bb4/xenoverse-0.1.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-18 07:50:48",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "FutureAGI",
"github_project": "xenoverse",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "gymnasium",
"specs": [
[
">=",
"1.0.0"
]
]
},
{
"name": "numpy",
"specs": [
[
">=",
"1.24.4"
]
]
},
{
"name": "Pillow",
"specs": [
[
">=",
"6.2.2"
]
]
},
{
"name": "six",
"specs": [
[
">=",
"1.12.0"
]
]
},
{
"name": "pygame",
"specs": [
[
">=",
"2.6.0"
]
]
},
{
"name": "numba",
"specs": [
[
">=",
"0.58.1"
]
]
}
],
"lcname": "xenoverse"
}
JSON
