Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating prediction outputs characterizing a set of entities. In one aspect, a method comprises: obtaining data defining a graph, comprising: (i) a set of nodes, wherein each node represents a respective entity from the set of entities, (ii) a current set of edges, wherein each edge connects a pair of nodes, and (iii) a respective current embedding of each node; at each of a plurality of time steps: updating the respective current embedding of each node, comprising processing data defining the graph using a graph neural network; and updating the current set of edges based at least in part on the updated embeddings of the nodes; and at one or more of the plurality of time steps: generating a prediction output characterizing the set of entities based on the current embeddings of the nodes.

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: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. In one aspect, a method of training an action selection policy neural network for use in selecting actions to be performed by an agent navigating through an environment to accomplish one or more goals comprises: receiving an observation image characterizing a current state of the environment; processing, using the action selection policy neural network, an input comprising the observation image to generate an action selection output; processing, using a geometry-prediction neural network, an intermediate output generated by the action selection policy neural network to predict a value of a feature of a geometry of the environment when in the current state; and backpropagating a gradient of a geometry-based auxiliary loss into the action selection policy neural network to determine a geometry-based auxiliary update for current values of the network parameters.

Abstract: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.

Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.

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: A neural network system is proposed 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 include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.

Abstract: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.

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: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.

Abstract: A neural network system is proposed 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 include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.

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: 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: There is described herein a computer-implemented method of processing an input data item. The method comprises processing the input data item using a parametric model to generate output data, wherein the parametric model comprises a first sub-model and a second sub-model. The processing comprises processing, by the first sub-model, the input data to generate a query data item, retrieving, from a memory storing data point-value pairs, at least one data point-value pair based upon the query data item and modifying weights of the second sub-model based upon the retrieved at least one data point-value pair. The output data is then generated based upon the modified second sub-model.

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: A system includes a neural network system implemented by one or more computers. The neural network system is configured to receive an observation characterizing a current state of a real-world environment being interacted with by a robotic agent to perform a robotic task and to process the observation to generate a policy output that defines an action to be performed by the robotic agent in response to the observation. The neural network system includes: (i) a sequence of deep neural networks (DNNs), in which the sequence of DNNs includes a simulation-trained DNN that has been trained on interactions of a simulated version of the robotic agent with a simulated version of the real-world environment to perform a simulated version of the robotic task, and (ii) a first robot-trained DNN that is configured to receive the observation and to process the observation to generate the policy output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. In one aspect, a method of training an action selection policy neural network for use in selecting actions to be performed by an agent navigating through an environment to accomplish one or more goals comprises: receiving an observation image characterizing a current state of the environment; processing, using the action selection policy neural network, an input comprising the observation image to generate an action selection output; processing, using a geometry-prediction neural network, an intermediate output generated by the action selection policy neural network to predict a value of a feature of a geometry of the environment when in the current state; and backpropagating a gradient of a geometry-based auxiliary loss into the action selection policy neural network to determine a geometry-based auxiliary update for current values of the network parameters.

Abstract: A system includes a neural network system implemented by one or more computers. The neural network system is configured to receive an observation characterizing a current state of a real-world environment being interacted with by a robotic agent to perform a robotic task and to process the observation to generate a policy output that defines an action to be performed by the robotic agent in response to the observation. The neural network system includes: (i) a sequence of deep neural networks (DNNs), in which the sequence of DNNs includes a simulation-trained DNN that has been trained on interactions of a simulated version of the robotic agent with a simulated version of the real-world environment to perform a simulated version of the robotic task, and (ii) a first robot-trained DNN that is configured to receive the observation and to process the observation to generate the policy output.

Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.

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.