TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization
机构 * School of Artificial Intelligence, Jilin University(人工智能学院,吉林大学)
专题命中 动作表示与策略 :vision-language-action(title);action model(title);VLA(abstract);分类 cs.RO、cs.AI