✳flâneur — a map of the web's best reading

Reinforcement learning from human feedback - Wikipedia

en.wikipedia.org · 9,174 words · saved by 1 readers

In machine learning, reinforcement learning from human feedback (RLHF), also known as reinforcement learning from human preferences, is a technique to align an intelligent agent to human preferences. In classical reinforcement learning, the goal of such an agent is to learn a function that guides its behavior called a policy. This function learns to maximize the reward it receives from a separate reward function based on its task performance.[1] In the case of human preferences, however, it tends to be difficult to define explicitly a reward function that approximates human preferences. Therefore, RLHF seeks to train a "reward model" directly from human feedback.[2] The reward model is first trained in a supervised fashion—independently from the policy being optimized—to predict if a response to a given prompt is good (high reward) or bad (low reward) based on ranking data collected from human annotators. This model is then used as a reward function to improve an agent's policy through

Reinforcement learning from human feedback - Wikipedia Jump to content From Wikipedia, the free encyclopedia Machine learning technique High-level overview of reinforcement learning from human feedback Part of a series on Machine learning and data mining Paradigms Supervised learning Unsupervised learning Semi-supervised learning Self-supervised learning Reinforcement learning Meta-learning Online learning Batch learning Curriculum learning Rule-based learning Neuro-symbolic AI Neuromorphic engineering Quantum machine learning Problems Classification Generative modeling Regression Clustering D

Explore this link on the map →

related reading