# Navigation MDP
A simple library for experimenting with Markov Decision Process (MDP). Designed specifically for studying Navigation problems.
MDP is defined by states S, dynamics T, actions A, and rewards R. The design philosophy of this library is that each entity in the MDP is a separate object. State is the central entity. Everything else is optional, and can be defined and attached to the states as per the need.
## Installation
To install current release with [pip](https://pypi.python.org/pypi/pip):
pip install navigation-mdp
To install from source:
python setup.py install
## Usage
If you're curious what it can do:
### 1. View examples in the notebook
[Navigation MDP](https://github.com/yrevar/navigation_mdp/blob/master/navigation_mdp.ipynb)
### 2. Play with it on Google Colab
[](https://colab.research.google.com/github/yrevar/navigation_mdp/blob/master/navigation_mdp.ipynb)
### 3. Play with it on MyBinder
[](https://mybinder.org/v2/gh/yrevar/navigation_mdp/master?urlpath=https%3A%2F%2Fgithub.com%2Fyrevar%2Fnavigation_mdp%2Fblob%2Fmaster%2Fnavigation_mdp.ipynb)
## Example
Create a 3 x 3 state space:
S = DiscreteStateSpace(3,3)
Attach indicator features:
S.attach_feature_spec(FeatureStateIndicatorOneHot("ind"))
Visualize the world:
p = NavGridView(S.features(key="ind", gridded=True)[..., np.newaxis, np.newaxis]).render().ticks().grid()
plt.colorbar(p.im)
## Dependency
For visualizations: https://github.com/yrevar/navigation_vis
# Acknowledgements
- Thanks to Prof. Michael L. Littman, Dr. Lucas Lehnert, and Dr. David Abel for all the discussions which were very helpful in developing concepts.
- State class is inspired from Dr. Abel's Simple RL framework: https://github.com/david-abel/simple_rl
Raw data
{
"_id": null,
"home_page": "https://github.com/yrevar/navigation_mdp",
"name": "navigation-mdp",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "Markov Decision Process,MDP,Navigation",
"author": "Yagnesh Revar",
"author_email": "mailto.yagnesh+github@gmail.com",
"download_url": "",
"platform": null,
"description": "# Navigation MDP\n\nA simple library for experimenting with Markov Decision Process (MDP). Designed specifically for studying Navigation problems.\n\nMDP is defined by states S, dynamics T, actions A, and rewards R. The design philosophy of this library is that each entity in the MDP is a separate object. State is the central entity. Everything else is optional, and can be defined and attached to the states as per the need.\n\n## Installation\n\nTo install current release with [pip](https://pypi.python.org/pypi/pip):\n\n pip install navigation-mdp\n\n\nTo install from source:\n\n python setup.py install\n\n\n\n## Usage\nIf you're curious what it can do:\n\n### 1. View examples in the notebook\n[Navigation MDP](https://github.com/yrevar/navigation_mdp/blob/master/navigation_mdp.ipynb)\n\n### 2. Play with it on Google Colab\n[](https://colab.research.google.com/github/yrevar/navigation_mdp/blob/master/navigation_mdp.ipynb)\n \n\n### 3. Play with it on MyBinder\n[](https://mybinder.org/v2/gh/yrevar/navigation_mdp/master?urlpath=https%3A%2F%2Fgithub.com%2Fyrevar%2Fnavigation_mdp%2Fblob%2Fmaster%2Fnavigation_mdp.ipynb)\n\n## Example\nCreate a 3 x 3 state space:\n\n S = DiscreteStateSpace(3,3)\n\n\nAttach indicator features:\n\n S.attach_feature_spec(FeatureStateIndicatorOneHot(\"ind\"))\n\nVisualize the world:\n\n p = NavGridView(S.features(key=\"ind\", gridded=True)[..., np.newaxis, np.newaxis]).render().ticks().grid()\n plt.colorbar(p.im)\n\n## Dependency\nFor visualizations: https://github.com/yrevar/navigation_vis\n\n# Acknowledgements\n- Thanks to Prof. Michael L. Littman, Dr. Lucas Lehnert, and Dr. David Abel for all the discussions which were very helpful in developing concepts. \n- State class is inspired from Dr. Abel's Simple RL framework: https://github.com/david-abel/simple_rl \n\n\n",
"bugtrack_url": null,
"license": "",
"summary": "A lightweight library for defining navigation grid world",
"version": "1.2",
"project_urls": {
"Homepage": "https://github.com/yrevar/navigation_mdp"
},
"split_keywords": [
"markov decision process",
"mdp",
"navigation"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "bd114b1349deddb0fea75ae0490b2a7747749246d7d02b341dd53fb736b88b30",
"md5": "e754ec823f1da7c8335b13d05c2d8604",
"sha256": "9d6e7cfcd493ee8867e8b0ea1619dd08820546e13a5a3974ad84489f1061c2a1"
},
"downloads": -1,
"filename": "navigation_mdp-1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e754ec823f1da7c8335b13d05c2d8604",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 18083,
"upload_time": "2024-02-09T19:30:09",
"upload_time_iso_8601": "2024-02-09T19:30:09.884396Z",
"url": "https://files.pythonhosted.org/packages/bd/11/4b1349deddb0fea75ae0490b2a7747749246d7d02b341dd53fb736b88b30/navigation_mdp-1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-09 19:30:09",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "yrevar",
"github_project": "navigation_mdp",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "navigation-mdp"
}
JSON
