alphaXiv

Explore

State of the Art

Sign In

Labs

Feedback

Browser Extension

We're hiring
PaperBlogResources

VinePPO: Refining Credit Assignment in RL Training of LLMs

BibTex
Copy
@Article{Kazemnejad2024VinePPOUR,
 author = {Amirhossein Kazemnejad and Milad Aghajohari and Eva Portelance and Alessandro Sordoni and Siva Reddy and Aaron C. Courville and Nicolas Le Roux},
 booktitle = {arXiv.org},
 journal = {ArXiv},
 title = {VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment},
 volume = {abs/2410.01679},
 year = {2024}
}
GitHub
VinePPO
121
HTTPS
https://github.com/McGill-NLP/VinePPO
SSH
git@github.com:McGill-NLP/VinePPO.git
CLI
gh repo clone McGill-NLP/VinePPO
Transform this paper into an audio lecture
Get an engaging lecture and Q&A format to quickly understand the paper in minutes, perfect for learning on the go.
Audio lecture
Q&A format