policy
dpo-ppo-rlhf-reward-modeling
xiuqi-zhu · PyTorch
or hover any field below to flag it
Overview
Name
dpo-ppo-rlhf-reward-modeling
Author
xiuqi-zhu
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
train a preference reward model, run DPO fine-tuning, and compare direct optimization with classical PPO-style RLHF pipelines.
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list dpo-ppo-rlhf-reward-modeling yet.
Datasets that reference this policy
0No datasets reference dpo-ppo-rlhf-reward-modeling yet.