2 citations · 2 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs
Nicolas Le Roux, Marc G. Bellemare, Jonathan Lebensold +7
We propose a new algorithm for fine-tuning large language models using reinforcement learning. Tapered Off-Policy REINFORCE (TOPR) uses an asymmetric, tapered variant of importance…
cs.LG2022★ 2 cited
Learning Robust Real-Time Cultural Transmission without Human Data
Cultural General Intelligence Team, Avishkar Bhoopchand, Bethanie Brownfield +16
Cultural transmission is the domain-general social skill that allows agents to acquire and use information from each other in real-time with high fidelity and recall. In humans, it…