Discrete Natural Evolution Strategies
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911820270272512 |
|---|---|
| author | Amin, Ahmad Ayaz |
| author_facet | Amin, Ahmad Ayaz |
| contents | Natural evolution strategies are a class of approximate-gradient black-box optimizers that have been successfully used for continuous parameter spaces. In this paper, we derive NES algorithms for discrete parameter spaces and demonstrate their effectiveness in tasks involving discrete parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00208 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Discrete Natural Evolution Strategies Amin, Ahmad Ayaz Neural and Evolutionary Computing Optimization and Control Natural evolution strategies are a class of approximate-gradient black-box optimizers that have been successfully used for continuous parameter spaces. In this paper, we derive NES algorithms for discrete parameter spaces and demonstrate their effectiveness in tasks involving discrete parameters. |
| title | Discrete Natural Evolution Strategies |
| topic | Neural and Evolutionary Computing Optimization and Control |
| url | https://arxiv.org/abs/2404.00208 |