melikbugra / Q-Learning-Theory-with-an-Expamle-for-Beginners

Basic Reinforcement Learning (RL) Theory with a Solution of a Simplified GridWorld Problem Using Q-Learning

Q-Learning Theory with an Expamle for Beginners

Basic Reinforcement Learning (RL) Theory with a Solution of a Simplified GridWorld Problem Using Q-Learning

This is a Python notebook. We will be dealing with a grid world environment shown below and while coding it, we will not be using any RL packages: The agent must finish the maze without neither going outside of the grid world nor going on red cells.