Observation Encoding for Reinforcement Learning Agents in 3D Game Environments

IEEE Conference on Games (CoG), pp. 1–8

Abstract

Due to the increasing complexity of video game environments, automated testing via reinforcement learning agents has gained significance in production environments. This study explores the effectiveness of various observation encoding techniques on agents in navigating complex 3D game environments. The primary challenge addressed is the increasing difficulty of manually testing and navigating expansive and intricate game worlds. The research evaluates how different observation encodings influence agents’ training efficiency and navigation success across several environments. However, the study indicates that there is no universal encoding solution, with performance varying significantly depending on the environment. Conclusively, we suggest future research avenues, including the exploration of basic obstacle learning, imitation learning, parameter optimization, and the investigation of new observation mechanisms. This research provides insights into optimizing agent performance in 3D game development, highlighting the need for further study in observation encoding techniques.

Authors 3

1. Lennart Haase

   TU Dortmund University

   Affiliation as printed

   TU Dortmund University,Department of Computer Science,Dortmund,Germany

2. Nicolas Fischöder

   TU Dortmund University

   Affiliation as printed

   TU Dortmund University,Department of Computer Science,Dortmund,Germany

3. Igor Vatolkin Aachen Chair for AI Methodology (AIM)

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Chair for AI Methodology,Aachen,Germany