Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling a plurality of robots. One of the methods includes: obtaining state data representing a current state of the environment; generating, from the state data, graph data representing a graph of the current state of the environment; processing the graph data using a graph neural network to generate a graph output that comprises a respective updated feature representation for each of the robot nodes in the graph; and selecting, based on the graph output, a respective action to be performed by each of the robots.

Abstract: A mobile computing implemented platform is provided that enables the generation, and delivery of highly relevant content to the mobile device of a driver. The content is filtered based on the current location and direction of the driver, and content is generated and filtered based a crowd sourced model where a plurality of users who are driving within a similar locations are linked to one another via the platform for improved discovery of traffic conditions, and improved determination of user interest based on collective interest of the plurality of users. Various intelligent features are enabled by the platform.

Abstract: An electronic apparatus programmed with a first code stored in a non-volatile memory during normal operation is reprogrammed by writing into a temporary memory a second code having a portion for reprogramming the non-volatile memory and an instruction portion. At least the reprogramming portion of the second code is executed from the temporary memory to cause the second code to be programmed into the non-volatile memory to replace the first set of code in the non-volatile memory.