SynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrations
Fine-tuning Vision-Language-Action (VLA) models commonly relies on human teleoperation demonstrations, while reinforcement learning (RL) with sparse binary rewards faces an exploration challenge when successful trajectories are rarely sampled. We propose SynthDemo-RL, a teacher-student framework in which an automated t...
Hiroaki Kingetsu, Hiroaki Kurihara, Kaoru Yokoo et al.
· 0 citations