Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting an action to be performed by a reinforcement learning agent interacting with an environment. A current observation characterizing a current state of the environment is received. For each action in a set of multiple actions that can be performed by the agent to interact with the environment, a probability distribution is determined over possible Q returns for the action-current observation pair. For each action, a measure of central tendency of the possible Q returns with respect to the probability distributions for the action-current observation pair is determined. An action to be performed by the agent in response to the current observation is selected using the measures of central tendency.

Abstract: A system including one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to implement a memory and memory-based neural network is described. The memory is configured to store a respective memory vector at each of a plurality of memory locations in the memory. The memory-based neural network is configured to: at each of a plurality of time steps: receive an input; determine an update to the memory, wherein determining the update comprising applying an attention mechanism over the memory vectors in the memory and the received input; update the memory using the determined update to the memory; and generate an output for the current time step using the updated memory.

Abstract: A system for compressed data storage using a neural network. The system comprises a memory comprising a plurality of memory locations configured to store data; a query neural network configured to process a representation of an input data item to generate a query; an immutable key data store comprising key data for indexing the plurality of memory locations; an addressing system configured to process the key data and the query to generate a weighting associated with the plurality of memory locations; a memory read system configured to generate output memory data from the memory based upon the generated weighting associated with the plurality of memory locations and the data stored at the plurality of memory locations; and a memory write system configured to write received write data to the memory based upon the generated weighting associated with the plurality of memory locations.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting an action to be performed by a reinforcement learning agent. The method includes obtaining an observation characterizing a current state of an environment. For each layer parameter of each noisy layer of a neural network, a respective noise value is determined. For each layer parameter of each noisy layer, a noisy current value for the layer parameter is determined from a current value of the layer parameter, a current value of a corresponding noise parameter, and the noise value. A network input including the observation is processed using the neural network in accordance with the noisy current values to generate a network output for the network input. An action is selected from a set of possible actions to be performed by the agent in response to the observation using the network output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the systems includes a memory interface subsystem that is configured to perform operations comprising determining a respective content-based weight for each of a plurality of locations in an external memory; determining a respective allocation weight for each of the plurality of locations in the external memory; determining a respective final writing weight for each of the plurality of locations in the external memory from the respective content-based weight for the location and the respective allocation weight for the location; and writing data defined by the write vector to the external memory in accordance with the final writing weights.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network. In one aspect, a method includes maintaining data specifying, for each of the network parameters, current values of a respective set of distribution parameters that define a posterior distribution over possible values for the network parameter. A respective current training value for each of the network parameters is determined from a respective temporary gradient value for the network parameter. The current values of the respective sets of distribution parameters for the network parameters are updated in accordance with the respective current training values for the network parameters. The trained values of the network parameters are determined based on the updated current values of the respective sets of distribution parameters.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an adaptive audio-generation model. One of the methods includes generating an adaptive audio-generation model including learning a plurality of embedding vectors and parameter values of a neural network using training data comprising first text and audio data representing a plurality of different individual speakers speaking portions of the first text, wherein the plurality of embedding vectors represent respective voice characteristics of the plurality of different individual speakers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output sequence of audio data that comprises a respective audio sample at each of a plurality of time steps. One of the methods includes, for each of the time steps: providing a current sequence of audio data as input to a convolutional subnetwork, wherein the current sequence comprises the respective audio sample at each time step that precedes the time step in the output sequence, and wherein the convolutional subnetwork is configured to process the current sequence of audio data to generate an alternative representation for the time step; and providing the alternative representation for the time step as input to an output layer, wherein the output layer is configured to: process the alternative representation to generate an output that defines a score distribution over a plurality of possible audio samples for the time step.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network including a first subnetwork followed by a second subnetwork on training inputs by optimizing an objective function. In one aspect, a method includes processing a training input using the neural network to generate a training model output, including processing a subnetwork input for the training input using the first subnetwork to generate a subnetwork activation for the training input in accordance with current values of parameters of the first subnetwork, and providing the subnetwork activation as input to the second subnetwork; determining a synthetic gradient of the objective function for the first subnetwork by processing the subnetwork activation using a synthetic gradient model in accordance with current values of parameters of the synthetic gradient model; and updating the current values of the parameters of the first subnetwork using the synthetic gradient.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for predicting future states objects and relations in complex systems. One method includes receiving an input comprising states of multiple receiver entities and multiple sender entities, and attributes of multiple relationships between the multiple receiver entities and multiple sender entities; processing the received input using an interaction component to produce as output multiple effects of the relationships between the multiple receiver entities and multiple sender entities; and processing the states of the multiple receiver entities and multiple sender entities, and the multiple effects of the relationships between the multiple receiver entities and multiple sender entities using a dynamical component to produce as output a respective prediction of a subsequent state of each of the multiple receiver entities and multiple sender entities.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining a control policy for a vehicles or other robot through the performance of a reinforcement learning simulation of the robot.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network system used to control an agent interacting with an environment to perform a specified task. One of the methods includes causing the agent to perform a task episode in which the agent attempts to perform the specified task; for each of one or more particular time steps in the sequence: generating a modified reward for the particular time step from (i) the actual reward at the time step and (ii) value predictions at one or more time steps that are more than a threshold number of time steps after the particular time step in the sequence; and training, through reinforcement learning, the neural network system using at least the modified rewards for the particular time steps.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing video data. An example system receives video data and generates optical flow data. An image sequence from the video data is provided to a first 3D spatio-temporal convolutional neural network to process the image data in at least three space-time dimensions and to provide a first convolutional neural network output. A corresponding sequence of optical flow image frames is provided to a second 3D spatio-temporal convolutional neural network to process the optical flow data in at least three space-time dimensions and to provide a second convolutional neural network output. The first and second convolutional neural network outputs are combined to provide a system output.

Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an actor neural network used to select actions to be performed by an agent interacting with an environment. One of the methods includes obtaining a minibatch of experience tuples; and updating current values of the parameters of the actor neural network, comprising: for each experience tuple in the minibatch: processing the training observation and the training action in the experience tuple using a critic neural network to determine a neural network output for the experience tuple, and determining a target neural network output for the experience tuple; updating current values of the parameters of the critic neural network using errors between the target neural network outputs and the neural network outputs; and updating the current values of the parameters of the actor neural network using the critic neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a whitened neural network layer. One of the methods includes receiving an input activation generated by a layer before the whitened neural network layer in the sequence; processing the received activation in accordance with a set of whitening parameters to generate a whitened activation; processing the whitened activation in accordance with a set of layer parameters to generate an output activation; and providing the output activation as input to a neural network layer after the whitened neural network layer in the sequence.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using an image processing neural network system that includes a spatial transformer module. One of the methods includes receiving an input feature map derived from the one or more input images, and applying a spatial transformation to the input feature map to generate a transformed feature map, comprising: processing the input feature map to generate spatial transformation parameters for the spatial transformation, and sampling from the input feature map in accordance with the spatial transformation parameters to generate the transformed feature map.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using recurrent attention. One of the methods includes determining a location in the first image; extracting a glimpse from the first image using the location; generating a glimpse representation of the extracted glimpse; processing the glimpse representation using a recurrent neural network to update a current internal state of the recurrent neural network to generate a new internal state; processing the new internal state to select a location in a next image in the image sequence after the first image; and processing the new internal state to select an action from a predetermined set of possible actions.

Abstract: A reinforcement learning neural network system in which internal representations and policies are grounded in visual entities derived from image pixels comprises a visual entity identifying neural network subsystem configured to process image data to determine a set of spatial maps representing respective discrete visual entities. A reinforcement learning neural network subsystem processes data from the set of spatial maps and environmental reward data to provide action data for selecting actions to perform a task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using multi-task neural networks. One of the methods includes receiving a first network input and data identifying a first machine learning task to be performed on the first network input; selecting a path through the plurality of layers in a super neural network that is specific to the first machine learning task, the path specifying, for each of the layers, a proper subset of the modular neural networks in the layer that are designated as active when performing the first machine learning task; and causing the super neural network to process the first network input using (i) for each layer, the modular neural networks in the layer that are designated as active by the selected path and (ii) the set of one or more output layers corresponding to the identified first machine learning task.