A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913554671599616 |
|---|---|
| author | Ma, Guozheng Wang, Zhen Yuan, Zhecheng Wang, Xueqian Yuan, Bo Tao, Dacheng |
| author_facet | Ma, Guozheng Wang, Zhen Yuan, Zhecheng Wang, Xueqian Yuan, Bo Tao, Dacheng |
| contents | Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains. However, deploying visual RL techniques in the real world remains challenging due to their low sample efficiency and large generalization gaps. To tackle these obstacles, data augmentation (DA) has become a widely used technique in visual RL for acquiring sample-efficient and generalizable policies by diversifying the training data. This survey aims to provide a timely and essential review of DA techniques in visual RL in recognition of the thriving development in this field. In particular, we propose a unified framework for analyzing visual RL and understanding the role of DA in it. We then present a principled taxonomy of the existing augmentation techniques used in visual RL and conduct an in-depth discussion on how to better leverage augmented data in different scenarios. Moreover, we report a systematic empirical evaluation of DA-based techniques in visual RL and conclude by highlighting the directions for future research. As the first comprehensive survey of DA in visual RL, this work is expected to offer valuable guidance to this emerging field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_04561 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning Ma, Guozheng Wang, Zhen Yuan, Zhecheng Wang, Xueqian Yuan, Bo Tao, Dacheng Computer Vision and Pattern Recognition Artificial Intelligence Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains. However, deploying visual RL techniques in the real world remains challenging due to their low sample efficiency and large generalization gaps. To tackle these obstacles, data augmentation (DA) has become a widely used technique in visual RL for acquiring sample-efficient and generalizable policies by diversifying the training data. This survey aims to provide a timely and essential review of DA techniques in visual RL in recognition of the thriving development in this field. In particular, we propose a unified framework for analyzing visual RL and understanding the role of DA in it. We then present a principled taxonomy of the existing augmentation techniques used in visual RL and conduct an in-depth discussion on how to better leverage augmented data in different scenarios. Moreover, we report a systematic empirical evaluation of DA-based techniques in visual RL and conclude by highlighting the directions for future research. As the first comprehensive survey of DA in visual RL, this work is expected to offer valuable guidance to this emerging field. |
| title | A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2210.04561 |