Rohan Paul· @rohanpaul_ai · X·· 6 小时前AI 评分40
AI 导读
V0.5 同时训练两个目标:预测机器人的下一步动作,以及预测其摄像头接下来会看到什么。 视频预测只是为了教模型场景如何变化。 运行时,V0.5 直接输出动作,因此该策略无需在每个控制步骤生成视频,就能获得世界模型的场景理解能力。
正文
V0.5 trains on two objectives at once: predicting the robot’s next actions and predicting what its cameras will see next.
The video prediction is only there to teach the model how scenes change.
At runtime, V0.5 outputs actions directly, so the policy gets a world model’s scene understanding without generating video on every control step.
来源:Rohan Paul · x.com