AIbase
Product LibraryTool NavigationMCP

LoL-RL

Public

Advantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients

Creat2023-05-24T04:26:26
Update2024-11-12T19:34:09
26
Stars
0
Stars Increase

Related projects