Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs
Paper
•
2503.14286
•
Published
•
2
Ma
heurainbow
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
19 days ago
Tapered Off-Policy REINFORCE: Stable and efficient reinforcement
learning for LLMs
upvoted
a
paper
19 days ago
ShiQ: Bringing back Bellman to LLMs
liked
a dataset
5 months ago
WizzF/Heap-Forge
Organizations
heurainbow's activity
upvoted
2
papers
19 days ago