Reinforcement learning seeks to teach agents to solve problems using numerical rewards as feedback. This makes it possible to incentivize actions that maximize returns despite having no initial strategy or knowledge of their environment. We implement a zero-external-dependency Q-learning algorithm using Python to optimally solve the single-player game JumpIn’ from SmartGames. We focus on interpretability of the model using Q-table parsing, and transferability to other games through a modular code structure. We observe rapid performance gains using our backtracking update algorithm.
Submission selected as one of 20 finalists in the Student Abstract category.