Solving JumpIN’ Using Zero-Dependency Reinforcement Learning (Student Abstract)

Abstract

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.

Rachel Ostic

Data scientist

I’m fascinated by data analysis and how it combines abstract thinking with real world problems, and I am starting to fuse this interest with programming both personally and at work.