ernie-research/TLDR-Gemma-2B-MA-PPO-Fixed5
3B
•
Updated
•
10
Macro-Action RLHF
[ICLR'25] [MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions](https://openreview.net/forum?id=WWXjMYZxfH)
-
-
ernie-research/HH-RLHF-Gemma-2B-MA-PPO-Fixed5
3B • Updated • 18 -
ernie-research/TLDR-Gemma-7B-MA-PPO-Fixed5
9B • Updated • 13 -
ernie-research/APPS-Gemma-7B-MA-PPO-Fixed10
9B • Updated • 42 -
ernie-research/HH-RLHF-Gemma-7B-MA-PPO-Fixed5
9B • Updated • 34 -
ernie-research/APPS-Gemma-2B-MA-PPO-Fixed10
3B • Updated • 9 -
ernie-research/TLDR-Gemma-2-27B-MA-PPO-Fixed5
27B • Updated • 35