RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback
arxiv.org · 6,853 words · saved by 1 readers
N/A
RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback Yufei Wang * 1 Zhanyi Sun * 1 Jesse Zhang 2 Zhou Xian 1 Erdem Bıyık 2 David Held † 1 Zackory Erickson † 1 Abstract as reward engineering, demands considerable human effort and trial-and-error…
saved by
related reading
- 2310.12921.pdfarxiv.org
- 2307.12950.pdfarxiv.org
- Illustrating Reinforcement Learning from Human Feedback (RLHF)huggingface.co
- [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
- SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningalphaxiv.org
- RLHF | John Lambertjohnwlambert.github.io
- Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts | RLHFlowrlhflow.github.io
- [2309.00267] RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackarxiv.org
- 2401.10020.pdfarxiv.org
- [2109.01115] Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationarxiv.org
- [2509.02722] Planning with Reasoning using Vision Language World Modelarxiv.org
- Checklists Are Better Than Reward Models For Aligning Language Modelsmachinelearning.apple.com