Sign in

A Survey of Reinforcement Learning from Human Feedback

By Timo Kaufmann and others at
LogoLMU Munich
Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of preference-based reinforcement learning (PbRL), it stands at the intersection of artificial intelligence and human-computer interaction.... Show more
April 30, 2024
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
A Survey of Reinforcement Learning from Human Feedback
Click on play to start listening