Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?

Kristian Gonzalez Barman Simon Lohse Henk W. de Regt

Published in: CoRR (2024)

Keyphrases

reinforcement learning
human subjects
state space
attribute values
function approximation
multi agent
human behavior
human interaction
human operators
reinforcement learning methods
standard deviation
model free
multiple perspectives
visual feedback
feedback mechanisms
user engagement