Generalist：GEN-1.5 上下文学习跨越仿真到现实差距
In-context learning also crosses the sim-to-real gap, zero-shot. Prompts can be formed entirely from simulated experience (e.g., from a scripted policy, an RL a
AI 导读
上下文学习也能零样本跨越仿真到现实的差距。提示词可以完全由仿真经验构成（例如来自脚本化策略、RL 智能体，或人类遥操作仿真机器人），并用于在真实机器人上产生行为。该模型既未在仿真器中、也未在真实世界中针对该任务训练过。
正文
当前显示原文，中文全文译文尚未就绪。
In-context learning also crosses the sim-to-real gap, zero-shot. Prompts can be formed entirely from simulated experience (e.g., from a scripted policy, an RL agent, or a human teleoperating a simulated robot) and be used to produce behaviors on a real robot. The model was not trained on the task in either the simulator or the real world.