視覚強化学習における無制限データ拡張のレシピ
A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning
視覚ベースの強化学習において、任意のデータ拡張を安定して適用できる汎用的な手法SADAを提案し、訓練の安定性と汎化性能を大幅に向上させた。
著者: Abdulaziz Almuzairee, Nicklas Hansen, Henrik I. Christensen
分類: cs.LG, cs.CV, cs.RO
原文アブストラクト
Q-learning algorithms are appealing for real-world applications due to their data-efficiency, but they are very prone to overfitting and training instabilities when trained from visual observations. Prior work, namely SVEA, finds that selective application of data augmentation can improve the visual generalization of RL agents without destabilizing training. We revisit its recipe for data augmentation, and find an assumption that limits its effectiveness to augmentations of a photometric nature. Addressing these limitations, we propose a generalized recipe, SADA, that works with wider varieties of augmentations. We benchmark its effectiveness on DMC-GB2 - our proposed extension of the popular DMControl Generalization Benchmark - as well as tasks from Meta-World and the Distracting Control Suite, and find that our method, SADA, greatly improves training stability and generalization of RL agents across a diverse set of augmentations. For visualizations, code and benchmark: see https://aalmuzairee.github.io/SADA/
