Metadata-Version: 2.1
Name: LearningNashQLearning
Version: 0.12
Summary: A simple NashQ-learning implementation in Python
Author: Paolo Ginefra, Federico Rocca, Andrea Tarabotto
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: matplotlib
Requires-Dist: seaborn
Requires-Dist: networkx
Requires-Dist: pygambit
Requires-Dist: netgraph
Requires-Dist: ipywidgets
Requires-Dist: notebook
Requires-Dist: ipympl

# LearningNashQLearning

This is an educational project to see the inner workings of the Nash-Q Learning algorithm. The Nash-Q Learning algorithm is a multi-agent reinforcement learning algorithm that is designed to learn Nash equilibria in general-sum stochastic games. This project is designed to be educational and is not intended to be used in production environments.

## What's in here?

You can find the following subpackages in this project:

- **Model**: Contains the implementation of the Nash-Q Learning algorithm as well as a wide range of classes to define Stochastic Games.
- **View**: Contains the implementation of a wide variety of widgets to visualize the Nash-Q Learning algorithm. They are designed to be used in python Notebooks via the ipythonwidgets library.
