A reinforcement learning project using Dynamic Programing
Run the application using:
$pipenv install --python 3.8 $pipenv shell $python app.py
Go to http://localhost:5000
Set the hyperparameters and click on SEND to see the agent trying to learn the path to the Goal. If you set a good reward for taking the treasure the agent may take it before search for the Goal. You can change the position of the Treasure and tha position of the Goal.