FIELD NOTES TOPIC
rl fine-tuning
1 note, newest first.
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
The paper introduces FORCE, a three-stage framework for improving the efficiency of fine-tuning Vision-Language-Action (VLA) models via Reinforcement Learning (RL). The framework addresses two main issues: initial…
