#artificial intelligence
Feb 2026
VLM-Guided Experience Replay
Across scenarios, including game-playing and robotics, spanning both discrete and continuous domains, agents trained with the proposed prioritization method achieve 15-57% higher average success rates and improve sample efficiency by 35-55% compared to previous approaches.
Elad Sharony, Tom Jurgenson, Orr Krupnik et al.
· arXiv.org · 0 citations