Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs
Paper
•
2503.14286
•
Published
•
1
Nicolas Le Roux
nicolouchka
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
13 days ago
Tapered Off-Policy REINFORCE: Stable and efficient reinforcement
learning for LLMs
authored
a paper
11 months ago
Towards Modular LLMs by Building and Reusing a Library of LoRAs
authored
a paper
almost 2 years ago
Deep Language Networks: Joint Prompt Training of Stacked LLMs using
Variational Inference
Organizations
