LoL-RL
PublicAdvantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients
Creat:2023-05-24T04:26:26
Update:2024-11-12T19:34:09
26
Stars
0
Stars Increase
Advantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients