Under the Personalized Assistant that Learns (PAL) program of the Defense Advanced Research Projects Agency (DARPA), we are working with SRI and other team-members on the CALO (Cognitive Agent that Learns and Organizes) project. The goal of this project is to create personal digital assistants that will learn from observation, experience, and by interacting with and being advised by its human users. These agents can be told what to do, and they will know and will be able to explain what they are doing. They will be able to respond to surprise in a robust manner, and they will interact with each other to handle a broad range of inter-related decision-making tasks. These computational agents will have the ability to engage in and lead routine tasks, and to assist when the unexpected happens.
Un experimento interesante !!!
No hay comentarios.:
Publicar un comentario