Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes sampling a behavior modulation in accordance with a current probability distribution; for each of one or more time steps: processing an input comprising an observation characterizing a current state of the environment at the time step using an action selection neural network to generate a respective action score for each action in a set of possible actions that can be performed by the agent; modifying the action scores using the sampled behavior modulation; and selecting the action to be performed by the agent at the time step based on the modified action scores; determining a fitness measure corresponding to the sampled behavior modulation; and updating the current probability distribution over the set of possible behavior modulations using the fitness measure corresponding to the behavior modulation.

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: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for bandwidth extension. One of the methods includes obtaining a low-resolution version of an input, the low-resolution version of the input comprising a first number of samples at a first sample rate over a first time period; and generating, from the low-resolution version of the input, a high-resolution version of the input comprising a second, larger number of samples at a second, higher sample rate over the first time period. Generating the high-resolution version includes generating a representation of the low-resolution version of the input; processing the representation of the low-resolution version of the input through a conditioning neural network to generate a conditioning input; and processing the conditioning input using a generative neural network to generate the high/resolution version of the input.

Abstract: A system including an attention neural network that is configured to receive an input sequence and to process the input sequence to generate an output is described. The attention neural network includes: an attention block configured to receive a query input, a key input, and a value input that are derived from an attention block input. The attention block includes an attention neural network layer configured to: receive an attention layer input derived from the query input, the key input, and the value input, and apply an attention mechanism to the query input, the key input, and the value input to generate an attention layer output for the attention neural network layer; and a gating neural network layer configured to apply a gating mechanism to the attention block input and the attention layer output of the attention neural network layer to generate a gated attention output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating audio output samples predicted to be communicated by a user. One example system includes a first user device having a first user. The first user device initiates a communication session between the first user and a second user of a second user device. The first user device obtains a neural network model of the second user. The neural network model is trained to generate, conditioned on audio input samples received up to a current time step, an audio output sample predicted to be communicated by the second user at a next time step. The user device repeatedly provides received audio input samples as input to the neural network model and plays audio output samples generated by the neural network model in place of received audio input samples communicated by the second user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for compressed sensing using neural networks. One of the methods includes receiving an input measurement of an input data item; for each of one or more optimization steps: processing a latent representation using a generator neural network to generate a candidate reconstructed data item, processing the candidate reconstructed data item using a measurement neural network to generate a measurement of the candidate reconstructed data item, and updating the latent representation to reduce an error between the measurement and the input measurement; and processing the latent representation after the one or more optimization steps using the generator neural network to generate a reconstruction of the input data item.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scalable continual learning using neural networks. One of the methods includes receiving new training data for a new machine learning task; training an active subnetwork on the new training data to determine trained values of the active network parameters from initial values of the active network parameters while holding current values of the knowledge parameters fixed; and training a knowledge subnetwork on the new training data to determine updated values of the knowledge parameters from the current values of the knowledge parameters by training the knowledge subnetwork to generate knowledge outputs for the new training inputs that match active outputs generated by the trained active subnetwork for the new training inputs.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes a plurality of workers, wherein each worker is configured to operate independently of each other worker, and wherein each worker is associated with a respective actor that interacts with a respective replica of the environment during the training of the deep neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting machine learning language models using search engine results. One of the methods includes obtaining question data representing a question; generating, from the question data, a search engine query for a search engine; obtaining a plurality of documents identified by the search engine in response to processing the search engine query; generating, from the plurality of documents, a plurality of conditioning inputs each representing at least a portion of one or more of the obtained documents; for each of a plurality of the generated conditioning inputs, processing a network input generated from (i) the question data and (ii) the conditioning input using a neural network to generate a network output representing a candidate answer to the question; and generating, from the network outputs representing respective candidate answers, answer data representing a final answer to the question.

Abstract: A method of training an action selection neural network to perform a demonstrated task using a supervised learning technique. The action selection neural network is configured to receive demonstration data comprising actions to perform the task and rewards received for performing the actions. The action selection neural network has auxiliary prediction task neural networks on one or more of its intermediate outputs. The action selection policy neural network is trained using multiple combined losses, concurrently with the auxiliary prediction task neural networks.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a system includes a language encoder model that is configured to receive a text string in a particular natural language, and process the text string to generate a text embedding of the text string. The system includes an observation encoder neural network that is configured to receive an observation characterizing a state of the environment, and process the observation to generate an observation embedding of the observation. The system includes a subsystem that is configured to obtain a current text embedding of a current text string and a current observation embedding of a current observation. The subsystem is configured to select an action to be performed by the agent in response to the current observation.

Abstract: Methods and systems for determining an optimized setting for one or more process parameters of a machine learning training process. One of the methods includes processing a current network input using a recurrent neural network in accordance with first values of the network parameters to obtain a current network output, obtaining a measure of the performance of the machine learning training process with an updated setting defined by the current network output, and generating a new network input that comprises (i) the updated setting defined by the current network output and (ii) the measure of the performance of the training process with the updated setting defined by the current network output.

Abstract: Methods and systems for low-latency multi-constraint ranking of content items. One of the methods includes receiving a request to rank a plurality of content items for presentation to a user to maximize a primary objective subject to a plurality of constraints; initializing a dual variable vector; updating the dual variable vector, comprising: determining an overall objective score for the dual variable vector; identifying a plurality of candidate dual variable vectors that includes one or more neighboring node dual variable vectors; determining respective overall objective scores for each of the one or more candidate dual variable vectors; identifying the candidate with the best overall objective score; and determining whether to update the dual variable vector based on whether the identified candidate has a better overall objective score than the dual variable vector; and determining a final ranking for the content items based on the dual variable vector.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network that is configured to process an input observation to generate a latent representation of the input observation. In one aspect, a method includes: obtaining a sequence of observations; for each observation in the sequence of observations, processing the observation using the encoder neural network to generate a latent representation of the observation; for each of one or more given observations in the sequence of observations: generating a context latent representation of the given observation; and generating, from the context latent representation of the given observation, a respective estimate of the latent representations of one or more particular observations that are after the given observation in the sequence of observations.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to generate a ranking score for a network input. One of the methods includes generating training data and training the neural network on the training data. The training data includes a plurality of training pairs. The generating comprising: obtaining data indicating that a plurality of training network inputs were displayed in a user interface according to a presentation order, obtaining data indicating that a first training network input of the plurality of training network inputs has a positive label, determining that a second training network input of the plurality of training network inputs (i) has a negative label and (ii) is higher than the first training network input in the presentation order, and generating a training pair that includes the first training network input and the second training network input.

Abstract: A method is proposed for training a multitask computer system, such as a multitask neural network system. The system comprises a set of trainable workers and a shared module. The trainable workers and shared module are trained on a plurality of different tasks, such that each worker learns to perform a corresponding one of the tasks according to a respective task policy, and said shared policy network learns a multitask policy which represents common behavior for the tasks. The coordinated training is performed by optimizing an objective function comprising, for each task: a reward term indicative of an expected reward earned by a worker in performing the corresponding task according to the task policy; and at least one entropy term which regularizes the distribution of the task policy towards the distribution of the multitask policy.

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: There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.

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 a computer storage medium, for generating sequences of predicted observations, for example images. In one aspect, a system comprises a controller recurrent neural network, and a decoder neural network to process a set of latent variables to generate an observation. An external memory and a memory interface subsystem is configured to, for each of a plurality of time steps, receive an updated hidden state from the controller, generate a memory context vector by reading data from the external memory using the updated hidden state, determine a set of latent variables from the memory context vector, generate a predicted observation by providing the set of latent variables to the decoder neural network, write data to the external memory using the latent variables, the updated hidden state, or both, and generate a controller input for a subsequent time step from the latent variables.