Metadata-Version: 2.0
Name: adjsim
Version: 2.0.1
Summary: An Agent Based Modelling Engine tailored for Reinforcement Learning.
Home-page: https://github.com/SeverTopan/AdjSim
Author: Sever Topan
Author-email: UNKNOWN
License: GPL-3.0
Keywords: agent based modelling ABM reinforcement learning
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Requires-Python: >=3.5, <3.7
Requires-Dist: PyQt5 (==5.9)
Requires-Dist: matplotlib (==2.0)
Requires-Dist: numpy (==1.13)

AdjSim Simulation Framework
===========================

|Build Status| |Coverage Status| |License: GPL v3|

A simulation framework. Intended for simulation of ecosystems.

    Designed and developed by Sever Topan

Features
--------

Engine
~~~~~~

At its core, AdjSim is an agent-based modelling engine. It allows users
to define simulation environments through which agents interact through
ability casting and timestep iteration. The framework is targeted
towards agents that behave intelligently, for example a bacterium
chasing down food. However, the framework is extremely flexible - from
enabling physics simulation to defining an environment in which
`Conway's Game of
Life <https://en.wikipedia.org/wiki/Conway%27s_Game_of_Life>`__ plays
out! AdjSim aims to be a foundational architecture on top of which
reinforcement learning can be built.

Graphical Simulation Representation
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The simulation can be viewed in real time as it unfolds, with graphics
are rendered and animated using PyQt5. Below are four of the distinct
examples packadged with AdjSim, ranging from bacteria to moon system
simulation.

+-------------------+------------------------+
| |Bacteria Demo|   | |Predator Prey Demo|   |
+===================+========================+
| |GOL Demo|        | |Jupiter Demo|         |
+-------------------+------------------------+

Post Simulation Analysis Tools
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Agent properties can be marked for tracking during simulation, allowing
for viewing the results of these values once the simulation completes.
For example, we can track the population of each different type of
agent, or the efficacy of the agent's ability to meet its intelligence
module-defined goals.

|QLearning Graph| |Predator Prey Graph|

Intelligence Module
~~~~~~~~~~~~~~~~~~~

Perhaps the most computationally interesting aspect of AdjSim lies in
its intelligence module. It allows agents to set goals (for example, the
goal of a bacterium may be to maximize its calories), and assess its
actions in terms of its ability to meet its goals. This allows the
agents to learn which actions are best used in a given situation.
Currently the intelligence module implements
`Q-Learning <https://en.wikipedia.org/wiki/Q-learning>`__, but more
advanced reinforcement learning techniques are coming soon!

Installing and Running AdjSim
-----------------------------

It is reccommended to run AdjSim using virtual python environments
provided by Anaconda or Pip. The following describes the installation
procedure for each of these.

Clone the GitHub repository.

::

     git clone https://github.com/SeverTopan/AdjSim

Make sure Python 3.5 or greater are installed, then create a new
environment with it.

::

    # If using Virtualenv
    virtualenv --python=/usr/bin/python3.6 venv
    source venv/bin/activate

    # If using Anaconda
    conda create --name adjsim python=3.6
    activate adjsim

Install Dependencies.

::

     python setup.py install

Note: If you run into trouble importing PyQt5 when installing using the
setup.py file, try using

::

    pip install -e .

.. |Build Status| image:: https://travis-ci.org/SeverTopan/AdjSim.svg?branch=master
   :target: https://travis-ci.org/SeverTopan/AdjSim
.. |Coverage Status| image:: https://coveralls.io/repos/github/SeverTopan/AdjSim/badge.svg?branch=master
   :target: https://coveralls.io/github/SeverTopan/AdjSim?branch=master
.. |License: GPL v3| image:: https://img.shields.io/badge/License-GPL%20v3-blue.svg
   :target: https://www.gnu.org/licenses/gpl-3.0
.. |Bacteria Demo| image:: https://raw.githubusercontent.com/SeverTopan/AdjSim/master/gallery/images/readme_bacteria.png
.. |Predator Prey Demo| image:: https://raw.githubusercontent.com/SeverTopan/AdjSim/master/gallery/images/readme_predator_prey.png
.. |GOL Demo| image:: https://raw.githubusercontent.com/SeverTopan/AdjSim/master/gallery/images/readme_game_of_life.png
.. |Jupiter Demo| image:: https://raw.githubusercontent.com/SeverTopan/AdjSim/master/gallery/images/readme_jupiter_moon_system.png
.. |QLearning Graph| image:: https://raw.githubusercontent.com/SeverTopan/AdjSim/master/gallery/images/readme_individual_learning.png
.. |Predator Prey Graph| image:: https://raw.githubusercontent.com/SeverTopan/AdjSim/master/gallery/images/readme_predator_prey_population.png


