Abstract: A computer-implemented method of training a student machine learning system comprises receiving data indicating execution of an expert, determining one or more actions performed by the expert during the execution and a corresponding state-action Jacobian, and training the student machine learning system using a linear-feedback-stabilized policy. The linear-feedback-stabilized policy may be based on the state-action Jacobian. Also a neural network system for representing a space of probabilistic motor primitives, implemented by one or more computers. The neural network system comprises an encoder configured to generate latent variables based on a plurality of inputs, each input comprising a plurality of frames, and a decoder configured to generate an action based on one or more of the latent variables and a state.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection system using reinforcement learning techniques. In one aspect, a method comprises at each of multiple iterations: obtaining a batch of experience, each experience tuple comprising: a first observation, an action, a second observation, and a reward; for each experience tuple, determining a state value for the second observation, comprising: processing the first observation using a policy neural network to generate an action score for each action in a set of possible actions; sampling multiple actions from the set of possible actions in accordance with the action scores; processing the second observation using a Q neural network to generate a Q value for each sampled action; and determining the state value for the second observation; and determining an update to current values of the Q neural network parameters using the state values.

Abstract: Methods, systems, and computer media provide for identifying exclusion zones in frames of a video, aggregating those exclusion zones for a specified duration or number of frames, defining a inclusion zone within which overlaid content is eligible for inclusion, and providing overlaid content for inclusion in the inclusion zone. The exclusion zones can include regions in which significant features are detected such as text, human features, objects from a selected set of object categories, or moving objects.

Abstract: A computer-implemented method of training a student machine learning system comprises receiving data indicating execution of an expert, determining one or more actions performed by the expert during the execution and a corresponding state-action Jacobian, and training the student machine learning system using a linear-feedback-stabilized policy. The linear-feedback-stabilized policy may be based on the state-action Jacobian. Also a neural network system for representing a space of probabilistic motor primitives, implemented by one or more computers. The neural network system comprises an encoder configured to generate latent variables based on a plurality of inputs, each input comprising a plurality of frames, and a decoder configured to generate an action based on one or more of the latent variables and a state.

Abstract: A computer-implemented method of training a student machine learning system comprises receiving data indicating execution of an expert, determining one or more actions performed by the expert during the execution and a corresponding state-action Jacobian, and training the student machine learning system using a linear-feedback-stabilized policy. The linear-feedback-stabilized policy may be based on the state-action Jacobian. Also a neural network system for representing a space of probabilistic motor primitives, implemented by one or more computers. The neural network system comprises an encoder configured to generate latent variables based on a plurality of inputs, each input comprising a plurality of frames, and a decoder configured to generate an action based on one or more of the latent variables and a state.

Abstract: A computer-implemented method of training a student machine learning system comprises receiving data indicating execution of an expert, determining one or more actions performed by the expert during the execution and a corresponding state-action Jacobian, and training the student machine learning system using a linear-feedback-stabilized policy. The linear-feedback-stabilized policy may be based on the state-action Jacobian. Also a neural network system for representing a space of probabilistic motor primitives, implemented by one or more computers. The neural network system comprises an encoder configured to generate latent variables based on a plurality of inputs, each input comprising a plurality of frames, and a decoder configured to generate an action based on one or more of the latent variables and a state.