EasyGameRL: Modular Reinforcement Learning Framework for Learners and Educators, implemented in Unreal Engine 4

Reinforcement learning algorithms have been applied to many research areas in gaming and non-gaming applications. However, in gaming artificial intelligence (AI), existing reinforcement learning tools are aimed at experienced developers and not readily accessible to learners. The unpredictable nature of online learning is also a barrier for casual users. The EasyGameRL framework is a novel approach to the education of reinforcement learning in games using modular visual design patterns. Its software implementation in Unreal Engine 4 are modular, reusable, and applicable to multiple game scenarios. The pattern-based approach allows users to effectively utilize reinforcement learning in their games and visualize the components of the process. This would be helpful to AI learners, educators, designers and casual users alike.

Contributors: Rachael Versaw, Samantha Schultz, Kevin Lu

Principal Investigator: Richard Zhao

Details

See details in: https://doi.org/10.1145/3472538.3472583