AI 摘要
继EMPIRE后,Jim Fan团队发布ASPIRE,为机器人构建可自我进化、无限累积的技能库。编码智能体观察仿真和真实机器人的多模态感官轨迹,对控制程序进行进化搜索,将最佳策略蒸馏进不断扩展的库中。ASPIRE无需梯度下降或端到端策略,而是通过传递“技能知识”绕过sim2real和跨本体迁移难题,相比从头训练实现约10倍迁移学习token缩减。已在150+任务和90+技能上验证,计划开源全栈。
ENPIRE ->; ASPIRE, our 2nd work in the series for Physical AutoResearch. We are building the components for robot self-improvement, one /skill at a time.
Today, we give robots a /skills library that self-evolves and compounds indefinitely! Introducing ASPIRE: a robot solving its 100th task is no longer as clueles...