The Effect of Training Schedules on Morphological Robustness and Generalization
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914876942712832 |
|---|---|
| author | Barba, Edoardo Yaman, Anil Iacca, Giovanni |
| author_facet | Barba, Edoardo Yaman, Anil Iacca, Giovanni |
| contents | Robustness and generalizability are the key properties of artificial neural network (ANN)-based controllers for maintaining a reliable performance in case of changes. It is demonstrated that exposing the ANNs to variations during training processes can improve their robustness and generalization capabilities. However, the way in which this variation is introduced can have a significant impact. In this paper, we define various training schedules to specify how these variations are introduced during an evolutionary learning process. In particular, we focus on morphological robustness and generalizability concerned with finding an ANN-based controller that can provide sufficient performance on a range of physical variations. Then, we perform an extensive analysis of the effect of these training schedules on morphological generalization. Furthermore, we formalize the process of training sample selection (i.e., morphological variations) to improve generalization as a reinforcement learning problem. Overall, our results provide deeper insights into the role of variability and the ways of enhancing the generalization property of evolved ANN-based controllers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_13965 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Effect of Training Schedules on Morphological Robustness and Generalization Barba, Edoardo Yaman, Anil Iacca, Giovanni Neural and Evolutionary Computing Robustness and generalizability are the key properties of artificial neural network (ANN)-based controllers for maintaining a reliable performance in case of changes. It is demonstrated that exposing the ANNs to variations during training processes can improve their robustness and generalization capabilities. However, the way in which this variation is introduced can have a significant impact. In this paper, we define various training schedules to specify how these variations are introduced during an evolutionary learning process. In particular, we focus on morphological robustness and generalizability concerned with finding an ANN-based controller that can provide sufficient performance on a range of physical variations. Then, we perform an extensive analysis of the effect of these training schedules on morphological generalization. Furthermore, we formalize the process of training sample selection (i.e., morphological variations) to improve generalization as a reinforcement learning problem. Overall, our results provide deeper insights into the role of variability and the ways of enhancing the generalization property of evolved ANN-based controllers. |
| title | The Effect of Training Schedules on Morphological Robustness and Generalization |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2407.13965 |