Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
- ai-safety
- alpaca
- datasets
- deepspeed
96,838 visible repositories in the index
1–2 of 2 · Most stars
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.