🏢 School of Computer Science, University of Sydney
Offline Behavior Distillation
·1729 words·9 mins·
loading
·
loading
AI Generated
Machine Learning
Reinforcement Learning
🏢 School of Computer Science, University of Sydney
This paper introduces Offline Behavior Distillation (OBD) to synthesize compact expert behavioral data from massive sub-optimal RL data, enabling faster policy learning.