Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-driven robotic control. One of the methods includes maintaining robot experience data; obtaining annotation data; training, on the annotation data, a reward model; generating task-specific training data for the particular task, comprising, for each experience in a second subset of the experiences in the robot experience data: processing the observation in the experience using the trained reward model to generate a reward prediction, and associating the reward prediction with the experience; and training a policy neural network on the task-specific training data for the particular task, wherein the policy neural network is configured to receive a network input comprising an observation and to generate a policy output that defines a control policy for a robot performing the particular task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-driven robotic control. One of the methods includes maintaining robot experience data; obtaining annotation data; training, on the annotation data, a reward model; generating task-specific training data for the particular task, comprising, for each experience in a second subset of the experiences in the robot experience data: processing the observation in the experience using the trained reward model to generate a reward prediction, and associating the reward prediction with the experience; and training a policy neural network on the task-specific training data for the particular task, wherein the policy neural network is configured to receive a network input comprising an observation and to generate a policy output that defines a control policy for a robot performing the particular task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-driven robotic control. One of the methods includes maintaining robot experience data; obtaining annotation data; training, on the annotation data, a reward model; generating task-specific training data for the particular task, comprising, for each experience in a second subset of the experiences in the robot experience data: processing the observation in the experience using the trained reward model to generate a reward prediction, and associating the reward prediction with the experience; and training a policy neural network on the task-specific training data for the particular task, wherein the policy neural network is configured to receive a network input comprising an observation and to generate a policy output that defines a control policy for a robot performing the particular task.

Abstract: In general, the subject matter described in this specification can be embodied in methods, systems, and program products for identifying proximity of a mobile computing device to another mobile computing device. A computing system determines that a set of mobile computing devices are geographically proximate to a first mobile computing device based on identifying that each of the mobile computing devices received a first type of signal from an emitting device for which the first mobile computing device also received the first type of signal. The computing system determines a subset of the mobile computing devices that share a physical space with the first mobile computing device based on identifying that each of the mobile computing devices emitted a second type of signal that was detected by the first mobile computing device, or detected the second type of signal that was emitted by the first mobile computing device.

Abstract: In general, the subject matter described in this specification can be embodied in methods, systems, and program products for identifying proximity of a mobile computing device to another mobile computing device. A computing system determines that a set of mobile computing devices are geographically proximate to a first mobile computing device based on identifying that each of the mobile computing devices received a first type of signal from an emitting device for which the first mobile computing device also received the first type of signal. The computing system determines a subset of the mobile computing devices that share a physical space with the first mobile computing device based on identifying that each of the mobile computing devices emitted a second type of signal that was detected by the first mobile computing device, or detected the second type of signal that was emitted by the first mobile computing device.