My solution for a MARL problem on a Grid Environment with Q-tables.

To run the project, run:

• conda create --name env python=3.7
• pip install -r requirements.txt
• python run.py

To-do:

• Add direction to the state space
• Take user parameters through GUI
• Write environment as a separate class
• Take second best action when agents try to go over blocks or get out of the board