[3Win5] Poster session 3

[3Win5-14] Evaluation of Image Processing-based Data Augmentation for Atari Game AI using Decision Transformer

〇Tsuyoshi Takano¹, Hiroshi Kera¹, Kazuhiko Kawamoto¹ (1.Chiba University)

Keywords:Reinforcement Learning, Transformer, Atari, Data Augmentation, Image Processing

In online reinforcement learning (RL), image processing-based data augmentation improves data diversity and sample efficiency by exposing the model to varied observations. In contrast, offline RL relies on a fixed dataset, making dataset diversity a crucial factor in performance. Whether image augmentation is beneficial in offline RL remains an open question. In this study, we apply image processing techniques, such as rotation and translation, to augment the training data for Decision Transformer. By comparing an augmented dataset with a clean dataset in the Atari Breakout environment, we find that some image processing methods significantly reduce scores. This result suggests that increasing diversity while preserving critical game contexts and maintaining consistency with the original data distribution is crucial for effective data augmentation in offline RL.