Sample-efficient Adversarial Imitation Learningopen access
- Authors
- Jung, Dahuin; Lee, Hyungyu; Yoon, Sungroh
- Issue Date
- Jan-2024
- Publisher
- MICROTOME PUBL
- Keywords
- imitation learning; adversarial imitation learning; self-sup ervised learning; data efficiency
- Citation
- JOURNAL OF MACHINE LEARNING RESEARCH, v.25, pp 1 - 32
- Pages
- 32
- Journal Title
- JOURNAL OF MACHINE LEARNING RESEARCH
- Volume
- 25
- Start Page
- 1
- End Page
- 32
- URI
- https://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/49482
- ISSN
- 1532-4435
1533-7928
- Abstract
- Imitation learning, in which learning is performed by demonstration, has been studied and advanced for sequential decision-making tasks in which a reward function is not predefined. However, imitation learning methods still require numerous expert demonstration samples to successfully imitate an expert's behavior. To improve sample efficiency, we utilize self-supervised representation learning, which can generate vast training signals from the given data. In this study, we propose a self -sup ervised representation-based adversarial imitation learning method to learn state and action representations that are robust to diverse distortions and temporally predictive, on non -image control tasks. In particular, in comparison with existing self -sup ervised learning methods for tabular data, we propose a different corruption method for state and action representations that is robust to diverse distortions. We theoretically and empirically observe that making an informative feature manifold with less sample complexity significantly improves the performance of imitation learning. The proposed method shows a 39% relative improvement over existing adversarial imitation learning methods on MuJoCo in a setting limited to 100 expert state -action pairs. Moreover, we conduct comprehensive ablations and additional experiments using demonstrations with varying optimality to provide insights into a range of factors.
- Files in This Item
-
Go to Link
- Appears in
Collections - ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.