Artificial Intelligence
279 views
Reward Modeling
Quick Definition
Training models to predict human preferences for RLHF
Full Definition
Training a model to predict human preferences and provide reward signals for reinforcement learning from human feedback.
Examples
RLHF training pipeline, preference learning, alignment
Related Terms
rlhf
ai-alignment
reinforcement-learning
More Artificial Intelligence Terms
AutoML
Automation of the machine learning pipeline
Sentiment Analysis
NLP technique determining emotional tone in text
OCR
Technology converting images of text into machine-readable text
Diffusion Model
Generative model creating data by iteratively removing noise
Transfer Learning
Adapting a pre-trained model for a different related task
State Space Model
Architecture using linear attention for efficient sequence modeling