REBEL: Reinforcement Learning via Regressing Relative Rewards
Paper
•
2404.16767
•
Published
•
2
REBEL: Reinforcement Learning via Regressing Relative Reward
-
-
Cornell-AGI/REBEL-Llama-3-Armo-iter_1
Updated • 6 • 1 -
Cornell-AGI/REBEL-Llama-3-Armo-iter_2
Updated • 8 • 2 -
Cornell-AGI/REBEL-Llama-3-Armo-iter_3
Updated • 4 • 2 -
Cornell-AGI/Ultrafeedback-Llama-3-Armo-iter_1
Viewer • Updated • 56.1k • 41 -
Cornell-AGI/Ultrafeedback-Llama-3-Armo-iter_2
Viewer • Updated • 55.1k • 29 -
Cornell-AGI/Ultrafeedback-Llama-3-Armo-iter_3
Viewer • Updated • 44.6k • 29 • 1 -
Cornell-AGI/REBEL-Llama-3
Text Generation • Updated • 25 • 1 -
Cornell-AGI/REBEL-Llama-3-epoch_2
Text Generation • Updated • 22 • 3 -
Cornell-AGI/REBEL-OpenChat-3.5
Text Generation • Updated • 20 • 1