reinforcement learning from human feedback
Sign in to saveAlso known as RLHF
variant of reinforcement learning
In the Vinony graph
Vinony's link graph records 459 inbound references to reinforcement learning from human feedback, and connects out to artificial neural network, mathematical optimization and Claude (language model).
It is catalogued under topics including 2017 in artificial intelligence, Language modeling and Reinforcement learning.
Vinony links it to 20 Wikipedia language editions.
Wikidata facts
- Subclass of
- reinforcement learning
Show 1 more fact
- uses
- human
Sources (2)
via Wikidata · CC0
Connections
artificial neural network
Entity
mathematical optimization
Entity
Claude (language model)
Concept
sampling
Entity
reinforcement learning
Entity
maximum likelihood estimation
Entity
transformer
Entity
overfitting
Entity
Kullback–Leibler divergence
Entity
autoregressive model
Entity
explainable AI
Entity
online machine learning
Entity
stochastic gradient descent
Entity
Google
Organization
Artificial intelligence
Concept
Alan Turing
Entity
International Standard Book Number
Entity
ChatGPT
Concept
John von Neumann
Entity
digital object identifier
Entity