Machine Learning Solutions

Implementing the basic version of the gaming bot

In this section, we will be implementing a simple game. I have already defined the rules of this game. Just to remind you quickly, our agent, yellow block tries to reach either the red block or the green block. If the agent reaches the green block, we will receive + 1 as a reward. If it reaches the red block, we get -1. Each step the agent will take will be considered a - 0.04 reward. You can turn back the pages and refer to the section Rules for the game if you want. You can refer to the code for this basic version of a gaming bot by referring to this GitHub link: https://github.com/jalajthanaki/Q_learning_for_simple_atari_game.

For this game, the gaming world or the gaming environment is already ...