JaxUED: A simple and useable UED library in Jax
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910374812450816 |
|---|---|
| author | Coward, Samuel Beukman, Michael Foerster, Jakob |
| author_facet | Coward, Samuel Beukman, Michael Foerster, Jakob |
| contents | We present JaxUED, an open-source library providing minimal dependency implementations of modern Unsupervised Environment Design (UED) algorithms in Jax. JaxUED leverages hardware acceleration to obtain on the order of 100x speedups compared to prior, CPU-based implementations. Inspired by CleanRL, we provide fast, clear, understandable, and easily modifiable implementations, with the aim of accelerating research into UED. This paper describes our library and contains baseline results. Code can be found at https://github.com/DramaCow/jaxued. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13091 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | JaxUED: A simple and useable UED library in Jax Coward, Samuel Beukman, Michael Foerster, Jakob Machine Learning Artificial Intelligence We present JaxUED, an open-source library providing minimal dependency implementations of modern Unsupervised Environment Design (UED) algorithms in Jax. JaxUED leverages hardware acceleration to obtain on the order of 100x speedups compared to prior, CPU-based implementations. Inspired by CleanRL, we provide fast, clear, understandable, and easily modifiable implementations, with the aim of accelerating research into UED. This paper describes our library and contains baseline results. Code can be found at https://github.com/DramaCow/jaxued. |
| title | JaxUED: A simple and useable UED library in Jax |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.13091 |