K² · Inteligencia artificial
Enseñar robots con lenguaje, no con puntuaciones, mejora el aprendizaje de datos imperfectos
The authors propose a language-critique framework for imitation learning from suboptimal demonstrations that uses natural language as a structured supervision signal instead of scalar signals.
CY
DW
Chih-Han Yang, Dai-Jie Wu, Yun-Ping Huang et al.
6 autores · cs.LG, cs.AI
El vistazo de 30 segundos
Imagina que enseñas a alguien a cocinar mirando vídeos de cocineros mediocres.
- The method constructs language labels from demonstrations that describe current progress, identify suboptimal behaviors, and provide fine-grained corrective guidance.
- The authors introduce a language-critique loss that trains policies using these structured signals without reducing them to scalars.
- The loss is instantiated for both behavior cloning and diffusion policies, yielding two methods named LC-BC and LC-DP.