Provable Offline Reinforcement Learning with Human Feedback.

Wenhao Zhan Masatoshi Uehara Nathan Kallus Jason D. Lee Wen Sun

Published in: CoRR (2023)

Keyphrases

reinforcement learning
human subjects
real time
human operators
neural network
information retrieval
learning algorithm
state space
reinforcement learning algorithms
creative problem solving
transition model
sensory inputs
human interaction
human users
learning problems
video sequences
machine learning