AI RESEARCH
Reducing Oracle Feedback with Vision-Language Embeddings for Preference-Based RL
arXiv CS.LG
•
ArXi:2603.28053v1 Announce Type: new Preference-based reinforcement learning can learn effective reward functions from comparisons, but its scalability is constrained by the high cost of oracle feedback. Lightweight vision-language embedding (VLE) models provide a cheaper alternative, but their noisy outputs limit their effectiveness as standalone reward generators. To address this challenge, we propose ROVED, a hybrid framework that combines VLE-based supervision with targeted oracle feedback.