Rafael Rafailov

offline reinforcement learning (6) direct preference optimization (4) reward model (4) model-based reinforcement learning (4) reinforcement learning from human feedback (4) large language model (3) language model alignment (3) text generation (2) reinforcement learning (2) preference modeling (2) language model (2) preference optimization (1) self-supervised learning (1) few-shot learning (1) preference learning (1) transfer learning (1) sample efficiency (1) imitation learning (1) robot learning (1) text-to-image generation (1)