PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Piché, Alexandre, Kamalloo, Ehsan, Pardinas, Rafael, Chen, Xiaoyin, Bahdanau, Dzmitry
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.19128