Physical Intelligence 用自洽性提升世界模型评估
We found that the key to make this work is self-consistency: the model is trained to be self-consistent between a forward and inverse model (i.e., actions predi
AI 导读
我们发现，让这项工作奏效的关键是自洽性：模型被训练成在前向模型与逆向模型之间自洽（即用逆向动力学预测的动作，会导向与 ID 输入一致的状态），在不同相机之间自洽，并通过中止分布外的回合来在训练与测试之间保持自洽。 有与无自洽性的对比视频
正文
当前显示原文，中文全文译文尚未就绪。
We found that the key to make this work is self-consistency: the model is trained to be self-consistent between a forward and inverse model (i.e., actions predicted with inverse dynamics lead to states consistent with ID input), consistent across different cameras, and consistent between training and test by halting episodes that go out of distribution.
With and without self consistency comparison video