The Game Boy Learning Environment

E Fazzari and D Romano and F Falchi and C Stefanini, IEEE TRANSACTIONS ON GAMES, 17, 965-974 (2025).

DOI: 10.1109/TG.2025.3575527

In this article, we introduce the Game Boy Learning Environment (GLE), an innovative suite based on Nintendo Game Boy games, crafted to advance and evaluate deep reinforcement learning algorithms on rich and varied gameplay tasks. GLE offers a comprehensive selection of 11 Game Boy environments, spanning nine distinct titles. These environments represent a significant leap in complexity compared to previous endeavors, like the arcade learning environment, presenting challenges for reinforcement learning, such as intricate long-term planning, strategic foresight, and hierarchical decision-making, posing substantial difficulties even for proficient human players. We delineate the spectrum of available environments and furnish initial baseline results obtained through the development and assessment of intelligent agents, employing established AI methodologies to address individual levels or subtasks within these environments.

Return to Publications page