Abstract: A best available video stream is determined for each of multiple conference participants within a conference room including multiple cameras based on scores determined for video streams obtained from the cameras. The scores are determined based on representations of the conference participants within the video streams, for example, based on percentages of conference participant faces visible within the video streams, directions of conference participant faces relative to the cameras, directions of eye gaze of the conference participants relative to the cameras, and/or degrees to which conference participant faces are obscured within the video streams. The best available video streams are output for rendering within separate user interface tiles of conferencing software.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for planning the future trajectory of an autonomous vehicle in an environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a policy neural network. In one aspect, a method for training a policy neural network configured to receive a scene data input and to generate a policy output to be followed by a target agent comprises: maintaining a set of training data, the set of training data comprising (i) training scene inputs and (ii) respective target policy outputs; at each training iteration: generating additional training scene inputs; generating a respective target policy output for each additional training scene input using a trained expert policy neural network that has been trained to receive an expert scene data input comprising (i) data characterizing the current scene and (ii) data characterizing a future state of the target agent; updating the set of training data; and training the policy neural network on the updated set of training data.

Abstract: A method for performing one or more tasks, wherein each of the one or more tasks includes predicting behavior of one or more agents in an environment, the method comprising: obtaining a three-dimensional (3D) input tensor representing behaviors of the one or more agents in the environment across a plurality of time steps; generating an encoded representation of the 3D input tensor by processing the 3D input tensor using an encoder neural network, wherein 3D input tensor comprises a plurality of observed cells and a plurality of masked cells; and processing the encoded representation of the 3D input tensor using a decoder neural network to generate a 4D output tensor.