Zero-shot Preference Learning for Offline RL via Optimal Transport.

Runze Liu Yali Du Fengshuo Bai Jiafei Lyu Xiu Li

Published in: CoRR (2023)

Keyphrases

preference learning
reinforcement learning
gaussian processes
multi agent
closed form
dynamic programming
pairwise comparison
ordinal regression
data mining
objective function
active learning
semi supervised