-
Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
Paper • 2410.04612 • Published -
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 • 49
Cornell-AGI
university
AI & ML interests
Reinforcement Learning from Human Feedback
Organization Card
Collections
2
models
8
Cornell-AGI/REFUEL-Llama-3-Armo-iter_2
Updated
•
25
•
1
Cornell-AGI/REFUEL-Llama-3-Armo-iter_1
Updated
•
2
Cornell-AGI/REBEL-Llama-3-Armo-iter_3
Updated
•
5
•
2
Cornell-AGI/REBEL-Llama-3-Armo-iter_2
Updated
•
1
Cornell-AGI/REBEL-Llama-3-Armo-iter_1
Updated
•
6
•
1
Cornell-AGI/REBEL-Llama-3-epoch_2
Text Generation
•
Updated
•
17
•
3
Cornell-AGI/REBEL-Llama-3
Text Generation
•
Updated
•
24
•
1
Cornell-AGI/REBEL-OpenChat-3.5
Text Generation
•
Updated
•
14
•
1
datasets
9
Cornell-AGI/amazon_movie_tv_llama_mxbai
Viewer
•
Updated
•
17.1k
•
36
Cornell-AGI/amazon_movie_tv_item_mxbai
Viewer
•
Updated
•
4.82k
•
26
Cornell-AGI/REFUEL-Ultrainteract-Llama-3-Armo-iter_2
Viewer
•
Updated
•
116k
•
93
•
1
Cornell-AGI/REFUEL-Ultrainteract-Llama-3-Armo-iter_1
Viewer
•
Updated
•
64.6k
•
49
Cornell-AGI/REFUEL-UltraInteract-setting-two
Viewer
•
Updated
•
106k
•
57
Cornell-AGI/REFUEL-hh-setting-two
Viewer
•
Updated
•
165k
•
34
Cornell-AGI/Ultrafeedback-Llama-3-Armo-iter_1
Viewer
•
Updated
•
56.1k
•
52
Cornell-AGI/Ultrafeedback-Llama-3-Armo-iter_3
Viewer
•
Updated
•
44.6k
•
56
•
1
Cornell-AGI/Ultrafeedback-Llama-3-Armo-iter_2
Viewer
•
Updated
•
55.1k
•
41