What is Reinforcement learning from AI feedback (RLAIF)?

Reinforcement learning from AI feedback (RLAIF)

Reinforcement learning from AI feedback (RLAIF): Like RLHF, but the preference labels used to train the reward signal come from another AI model rather than from people.

Related terms

Reinforcement learning from human feedback (RLHF)
Inverse reinforcement learning
Model-based reinforcement learning
Offline reinforcement learning
Reinforcement learning (RL)
Reinforcement learning environment (RL environment)
Reinforcement learning with verifiable rewards (RLVR)
Automated machine learning (AutoML)

Browse the full glossary →