# `deluca`
Performant, differentiable reinforcement learning
## Notes
1. This is pre-alpha software and is undergoing a number of core changes. Updates to follow.
2. `deluca` is currently implemented as a minimal Python namespace package. It
will contain environments and agents that *only* depend on NumPy, along with
utilities for benchmarking, visualization, etc.
3. The remainder of environments are developed in separate plugins (also Python
namespace packages)
- [`deluca-jax`](https://github.com/MinRegret/deluca-jax): differentiable environments and relevant agents implemented
using `jax`
- [`deluca-lung`](https://pypi.org/project/deluca-lung/): differentiable lung simulators and relevant agents
implemented in `PyTorch`
4. Documentation forthcoming!
[](https://pypi.org/project/deluca/)
[](https://pypi.org/project/deluca)
[](https://github.com/PyCQA/bandit)
[](https://github.com/psf/black)
[](https://github.com/MinRegret/deluca/blob/dev/LICENSE)
[](https://github.com/MinRegret/deluca/actions)
[](https://codecov.io/github/MinRegret/deluca)
[](https://deluca.readthedocs.io/en/latest/?badge=latest)
[](https://github.com/MinRegret/deluca)
Raw data
{
"_id": null,
"home_page": "https://github.com/google/deluca",
"name": "deluca",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "differentiable,control algorithms,reinforcement learning",
"author": "Google AI Princeton",
"author_email": "dsuo@google.com",
"download_url": "https://files.pythonhosted.org/packages/d2/c7/94139464d61662208acc339a5f59d5c60e9cf376a7b53ad0e482328609ff/deluca-0.0.18.tar.gz",
"platform": null,
"description": "# `deluca`\n\nPerformant, differentiable reinforcement learning\n\n## Notes\n1. This is pre-alpha software and is undergoing a number of core changes. Updates to follow.\n2. `deluca` is currently implemented as a minimal Python namespace package. It\n will contain environments and agents that *only* depend on NumPy, along with\n utilities for benchmarking, visualization, etc.\n3. The remainder of environments are developed in separate plugins (also Python\n namespace packages)\n - [`deluca-jax`](https://github.com/MinRegret/deluca-jax): differentiable environments and relevant agents implemented\n using `jax`\n - [`deluca-lung`](https://pypi.org/project/deluca-lung/): differentiable lung simulators and relevant agents\n implemented in `PyTorch`\n4. Documentation forthcoming!\n\n[](https://pypi.org/project/deluca/)\n[](https://pypi.org/project/deluca)\n[](https://github.com/PyCQA/bandit)\n[](https://github.com/psf/black)\n[](https://github.com/MinRegret/deluca/blob/dev/LICENSE)\n\n[](https://github.com/MinRegret/deluca/actions)\n[](https://codecov.io/github/MinRegret/deluca)\n[](https://deluca.readthedocs.io/en/latest/?badge=latest)\n[](https://github.com/MinRegret/deluca)\n\n\n",
"bugtrack_url": null,
"license": "Apache License",
"summary": "",
"version": "0.0.18",
"project_urls": {
"Homepage": "https://github.com/google/deluca"
},
"split_keywords": [
"differentiable",
"control algorithms",
"reinforcement learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "d2c794139464d61662208acc339a5f59d5c60e9cf376a7b53ad0e482328609ff",
"md5": "a153634e1dee0db48d4121f4d177a1af",
"sha256": "5936eb490b7c3de9f2b81d4fafa6f9d256e428f33ab5a3790f837ccc21e1297d"
},
"downloads": -1,
"filename": "deluca-0.0.18.tar.gz",
"has_sig": false,
"md5_digest": "a153634e1dee0db48d4121f4d177a1af",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 10322,
"upload_time": "2023-12-05T17:14:23",
"upload_time_iso_8601": "2023-12-05T17:14:23.362757Z",
"url": "https://files.pythonhosted.org/packages/d2/c7/94139464d61662208acc339a5f59d5c60e9cf376a7b53ad0e482328609ff/deluca-0.0.18.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-05 17:14:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "google",
"github_project": "deluca",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "deluca"
}
JSON
