| Name | rldog JSON |
| Version |
0.1.0
JSON |
| download |
| home_page | |
| Summary | Core 4 Reinforcement learning algorithms, implemented with very high quality code (think type hints, tests, pep8 etc). Very easy to use with gym or gym-like environments |
| upload_time | 2023-01-03 19:36:19 |
| maintainer | |
| docs_url | None |
| author | Charlie |
| requires_python | >=3.10,<4.0 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# PyRL
Environment Agnostic RL algorithm implementations using Pytorch. High quality code, typehints, thorough tests, examples.
Also uses minibatches correctly, which most public libraries don't implement.
See examples for some, well, examples. Algos implemented:
1. *Deep Q Learning (DQN)* <sub><sup> ([Mnih et al. 2013](https://arxiv.org/pdf/1312.5602.pdf)) </sup></sub>
--- UPCOMING ---
2. *DQN Experience Replay* <sub><sup> ([Mnih et al. 2013](https://arxiv.org/pdf/1312.5602.pdf)) </sup></sub>
3. *DQN with Fixed targets* <sub><sup>([Mnih et al. 2013](https://arxiv.org/pdf/1312.5602.pdf)) </sup></sub>
4. *Double Q Learning (DDQN)* <sub><sup> ([arXiv:1509.06461v3 [cs.LG] 8 Dec 2015](https://arxiv.org/pdf/1509.06461v3.pdf)) </sup></sub>
5. REINFORCE <sub><sup> ([Richard S. Sutton et al 1999](https://proceedings.neurips.cc/paper/1999/file/464d828b85b0bed98e80ade0a5c43b0f-Paper.pdf))
6. Advantage Actor Critic ([arXiv:1611.06256](https://arxiv.org/abs/1611.06256))
3. PPO
What i'm happy with
Quality of the code, thorough tests, majority of functionality, ease of use & versatility
Run tests with: pytest tests
Raw data
{
"_id": null,
"home_page": "",
"name": "rldog",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.10,<4.0",
"maintainer_email": "",
"keywords": "",
"author": "Charlie",
"author_email": "CharlieJackCoding@Gmail.com",
"download_url": "https://files.pythonhosted.org/packages/39/cb/eb5943a97d3c3c1c3d50cb2d5a9757cd25f8bfbaabc6e68521b5843d92b4/rldog-0.1.0.tar.gz",
"platform": null,
"description": "# PyRL\nEnvironment Agnostic RL algorithm implementations using Pytorch. High quality code, typehints, thorough tests, examples.\nAlso uses minibatches correctly, which most public libraries don't implement.\n\n\nSee examples for some, well, examples. Algos implemented:\n\n1. *Deep Q Learning (DQN)* <sub><sup> ([Mnih et al. 2013](https://arxiv.org/pdf/1312.5602.pdf)) </sup></sub> \n --- UPCOMING ---\n2. *DQN Experience Replay* <sub><sup> ([Mnih et al. 2013](https://arxiv.org/pdf/1312.5602.pdf)) </sup></sub> \n3. *DQN with Fixed targets* <sub><sup>([Mnih et al. 2013](https://arxiv.org/pdf/1312.5602.pdf)) </sup></sub> \n4. *Double Q Learning (DDQN)* <sub><sup> ([arXiv:1509.06461v3 [cs.LG] 8 Dec 2015](https://arxiv.org/pdf/1509.06461v3.pdf)) </sup></sub> \n5. REINFORCE <sub><sup> ([Richard S. Sutton et al 1999](https://proceedings.neurips.cc/paper/1999/file/464d828b85b0bed98e80ade0a5c43b0f-Paper.pdf))\n6. Advantage Actor Critic ([arXiv:1611.06256](https://arxiv.org/abs/1611.06256))\n\n3. PPO\n\nWhat i'm happy with\nQuality of the code, thorough tests, majority of functionality, ease of use & versatility\n\nRun tests with: pytest tests",
"bugtrack_url": null,
"license": "MIT",
"summary": "Core 4 Reinforcement learning algorithms, implemented with very high quality code (think type hints, tests, pep8 etc). Very easy to use with gym or gym-like environments",
"version": "0.1.0",
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "1662435e95c330a100d91016c4cb7810b2b508c6517fa826ace277767ed21bf9",
"md5": "62fb85789bd3ad4be64c1d531da52a78",
"sha256": "7f2b6177fb0fbdd61ef7e5f210280cf911d4d036f10c08bf9fa9e915bfca2bd6"
},
"downloads": -1,
"filename": "rldog-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "62fb85789bd3ad4be64c1d531da52a78",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10,<4.0",
"size": 26659,
"upload_time": "2023-01-03T19:36:17",
"upload_time_iso_8601": "2023-01-03T19:36:17.520626Z",
"url": "https://files.pythonhosted.org/packages/16/62/435e95c330a100d91016c4cb7810b2b508c6517fa826ace277767ed21bf9/rldog-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "39cbeb5943a97d3c3c1c3d50cb2d5a9757cd25f8bfbaabc6e68521b5843d92b4",
"md5": "698b923ff35469abc02a17a4535d4752",
"sha256": "91024f94fa2c0376c453456c8d460f3f029c3ca695f9401ce453274fd6fb9682"
},
"downloads": -1,
"filename": "rldog-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "698b923ff35469abc02a17a4535d4752",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10,<4.0",
"size": 17512,
"upload_time": "2023-01-03T19:36:19",
"upload_time_iso_8601": "2023-01-03T19:36:19.157918Z",
"url": "https://files.pythonhosted.org/packages/39/cb/eb5943a97d3c3c1c3d50cb2d5a9757cd25f8bfbaabc6e68521b5843d92b4/rldog-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-01-03 19:36:19",
"github": false,
"gitlab": false,
"bitbucket": false,
"lcname": "rldog"
}
