howto.rl.005.rst

Howto 05 - (RL) Train multi-agent with own policy on multicartpole environment

Ver. 1.3.1 (2021-12-07)

This module shows how to train an own multi-agent with the enhanced multi-action environment MultiCartPole based on the OpenAI Gym CartPole environment.

Prerequisites

Please install the following packages to run this examples properly:

• :ref:`MLPro <Installation>`
• OpenAI Gym

Example Code

.. literalinclude:: ../../../../../examples/rl/Howto 05 - (RL) Train multi-agent with own policy on multicartpole environment.py
    :language: python

Results

...