XuanCe is an open-source ensemble of Deep Reinforcement Learning (DRL) algorithm implementations. We call it as Xuan-Ce (玄策) in Chinese. "Xuan (玄)" means incredible and magic box, "Ce (策)" means policy. DRL algorithms are sensitive to hyper-parameters tuning, varying in performance with different tricks, and suffering from unstable training processes, therefore, sometimes DRL algorithms seems elusive and "Xuan". This project gives a thorough, high-quality and easy-to-understand implementation of DRL algorithms, and hope this implementation can give a hint on the magics of reinforcement learning. We expect it to be compatible with multiple deep learning toolboxes( PyTorch, TensorFlow, and MindSpore), and hope it can really become a zoo full of DRL algorithms.
Raw data
{
"_id": null,
"home_page": null,
"name": "xuance",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "deep reinforcement learning, software library, PyTorch, TensorFlow2, MindSpore",
"author": "Wenzhang Liu, et al.",
"author_email": "liu_wzh@foxmail.com",
"download_url": "https://files.pythonhosted.org/packages/8b/60/8b89d6934374d6105ae1cdacf1b96a66d4d6b5bad5e90b961b35da5c6d8f/xuance-1.2.3.tar.gz",
"platform": null,
"description": "XuanCe is an open-source ensemble of Deep Reinforcement Learning (DRL) algorithm implementations. We call it as Xuan-Ce (\u7384\u7b56) in Chinese. \"Xuan (\u7384)\" means incredible and magic box, \"Ce (\u7b56)\" means policy. DRL algorithms are sensitive to hyper-parameters tuning, varying in performance with different tricks, and suffering from unstable training processes, therefore, sometimes DRL algorithms seems elusive and \"Xuan\". This project gives a thorough, high-quality and easy-to-understand implementation of DRL algorithms, and hope this implementation can give a hint on the magics of reinforcement learning. We expect it to be compatible with multiple deep learning toolboxes( PyTorch, TensorFlow, and MindSpore), and hope it can really become a zoo full of DRL algorithms.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library.",
"version": "1.2.3",
"project_urls": {
"Download": "https://github.com/agi-brain/xuance.git"
},
"split_keywords": [
"deep reinforcement learning",
" software library",
" pytorch",
" tensorflow2",
" mindspore"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "8b608b89d6934374d6105ae1cdacf1b96a66d4d6b5bad5e90b961b35da5c6d8f",
"md5": "e8722680a0a2b7bb006e8cfbcb8bf367",
"sha256": "5e4fec5d104d0993c5721c64d5dff2fa5b9b1ef93ca0c38aa547525b9e418d7b"
},
"downloads": -1,
"filename": "xuance-1.2.3.tar.gz",
"has_sig": false,
"md5_digest": "e8722680a0a2b7bb006e8cfbcb8bf367",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 354200,
"upload_time": "2024-09-11T14:04:08",
"upload_time_iso_8601": "2024-09-11T14:04:08.670680Z",
"url": "https://files.pythonhosted.org/packages/8b/60/8b89d6934374d6105ae1cdacf1b96a66d4d6b5bad5e90b961b35da5c6d8f/xuance-1.2.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-11 14:04:08",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "agi-brain",
"github_project": "xuance",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "xuance"
}
JSON
