Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
Paper
•
2410.04612
•
Published
Regressing the Relative Future: Efficient Policy Optimizatio
-
-
Cornell-AGI/REFUEL-Llama-3-Armo-iter_1
Updated • 2 -
Cornell-AGI/REFUEL-Llama-3-Armo-iter_2
Updated • 25 • 1 -
Cornell-AGI/REFUEL-Ultrainteract-Llama-3-Armo-iter_1
Viewer • Updated • 64.6k • 57 -
Cornell-AGI/REFUEL-Ultrainteract-Llama-3-Armo-iter_2
Viewer • Updated • 116k • 92 • 1 -
Cornell-AGI/REFUEL-hh-setting-two
Viewer • Updated • 165k • 32 -
Cornell-AGI/REFUEL-UltraInteract-setting-two
Viewer • Updated • 106k • 69