Piece by Piece: Assembling a Modular Reinforcement Learning Environment for Tetris

EasyChair Preprint 13437, version 2

Abstract

The game of Tetris is an open challenge in machine learning and especially Reinforcement Learning (RL). Despite its popularity, contemporary environments for the game lack key qualities, such as a clear documentation, an up-to-date codebase or game related features. This work introduces Tetris Gymnasium, a modern RL environment built with Gymnasium, that aims to address these problems by being modular, understandable and adjustable. To evaluate Tetris Gymnasium on these qualities, a Deep Q Learning agent was trained and compared to a baseline environment, and it was found that it fulfills all requirements of a feature-complete RL environment while being adjustable to many different requirements. The source-code and documentation is available at on GitHub and can be used for free under the MIT license (https://github.com/Max-We/Tetris-Gymnasium).

Keyphrases: Gymnasium, Reinforcement Learning, Software Engineering, Tetris, library

@booklet{EasyChair:13437,
  author    = {Maximilian Weichart and Philipp Hartl},
  title     = {Piece by Piece: Assembling a Modular Reinforcement Learning Environment for Tetris},
  howpublished = {EasyChair Preprint 13437},
  year      = {EasyChair, 2024}}