Technology: News & Insights
The researchers constructed two variations of a mannequin for robots, called RT-X, that could be both run domestically on particular person labs’ computer systems or accessed via the web. The larger, web-accessible model was pretrained with internet information to develop a “visual common sense,” or a baseline understanding of the world, from the large language and picture models. When the researchers ran the RT-X mannequin on many alternative robots, they found that the robots were in a position to learn abilities 50% extra efficiently than in the systems every particular person lab was developing. A new initiative kick-started by Google…