Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing.

Biqing Qi Pengfei Li Fangyuan Li Junqi Gao Kaiyan Zhang Bowen Zhou

Published in: CoRR (2024)

Keyphrases

online learning
real time
decision making
global optimization
optimization process
real world
artificial intelligence
knowledge base
data structure
decision makers
optimization algorithm
multi criteria
multiple criteria
soft constraints