Published March 4, 2024
| Version published
Software
Open
Genetic Learning for Designing Sim-to-Real Data Augmentations - Source Code DMLR Workshop @ ICLR
Creators
-
1.
Hasselt University
- 2. Digital Future Lab
-
3.
Flanders Make (Belgium)
Description
We analyze the benefit of data augmentations for overcoming the sim-to-real gap and use the results to develop a genetic learning algorithm for finding augmentation policies.
Source code for the following scientific publication:
Vanherle, Bram, Nick Michiels, and Frank Van Reeth. "Genetic Learning for Designing Sim-to-Real Data Augmentations." Workshop on Data-centric Machine Learning Research (DMLR) at International Conference on Learning Representations (ICLR 2024).
Files
EDM-Research/genetic-augment-published.zip
Files
(14.7 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:1b3b3f14337444c49467e92875c22f40
|
14.7 kB | Preview Download |
Additional details
Related works
- Is supplement to
- Software: https://github.com/EDM-Research/genetic-augment/tree/published (URL)
- Conference paper: 10.48550/arXiv.2403.06786 (DOI)
- Peer review: https://openreview.net/forum?id=02urt8Hb3n (URL)
Software
- Repository URL
- https://github.com/EDM-Research/genetic-augment
- Programming language
- Python
- Development Status
- Concept