Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating long textual works using language model neural networks. For example, the textual works can be generated hierarchically by performing a hierarchy of generation steps using the same language model neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for precipitation nowcasting using generative neural networks.

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, 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, 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, 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: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space.