Article
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
NormalUhr
• • 132
parsa rahimi
parano
·
AI & ML interests
Generative Models, Genrative Prior, Generative-AI, Controlled Generation, Synthetic Data
Organizations
upvoted an article about 1 year ago