Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent to interact with an environment using an action selection neural network. In one aspect, a method comprises, at each time step in a sequence of time steps: generating a current representation of a state of a task being performed by the agent in the environment as of the current time step as a sequence of data elements; autoregressively generating a sequence of data elements representing a current action to be performed by the agent at the current time step; and after autoregressively generating the sequence of data elements representing the current action, causing the agent to perform the current action at the current time step.

Abstract: A computer-implemented system and method for storing data associated with an agent in a multi-dimensional environment via a memory architecture. The memory architecture is structured so that each unique position in the environment corresponds to a unique position within the memory architecture, thereby allowing the memory architecture to store features located at a particular position in the environment in a memory location specific to that location. As the agent traverses the environment, the agent compares the features at the agent's particular position to a summary of the features stored throughout the memory architecture and writes the features that correspond to the summary to the coordinates in the memory architecture that correspond to the agent's position. The system and method allows agents to learn, using a reinforcement signal, how to behave when acting in an environment that requires storing information over long time steps.

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: In accordance with some embodiments, a method is performed at a device with one or more processors and non-transitory memory. The method includes obtaining location vector data characterizing an object. The method includes determining a neural pose graph associated with a respective time-period based on an initial local pose estimation as a function of respective location vector data. The method includes determining a meta pose estimation associated with the respective time-period by aggregating the neural pose graph associated with the respective time-period and one or more other neural pose graphs associated with one or more temporally adjacent time-periods.

Abstract: In accordance with some embodiments, a method is performed at a device with one or more processors and non-transitory memory. The method includes obtaining location vector data characterizing an object. The method includes determining a neural pose graph associated with a respective time-period based on an initial local pose estimation as a function of respective location vector data. The method includes determining a meta pose estimation associated with the respective time-period by aggregating the neural pose graph associated with the respective time-period and one or more other neural pose graphs associated with one or more temporally adjacent time-periods.

Abstract: Generally discussed herein are devices, systems, and methods for encoding input-output examples. A method of generating a program using an encoding of input-output examples, may include processing an input example of the input-output examples, using a first long short term memory (LSTM) neural network, one character at a time to produce an input feature vector, processing an output example associated with the input example in the input-output examples, using the LSTM neural network, one character at a time to produce an output feature vector, determining (a) a cross-correlation between the input feature vector and the output feature vector or (b) previously computed feature vectors for a different input-output example that are sufficiently close to the input feature vector and the output feature vector, respectively, and using the determined cross-correlation or previously computed vector, generating a program consistent with the input example and the output example.

Abstract: Described are systems, methods, and computer-readable media for program generation in a domain-specific language based on input-output examples. In accordance with various embodiments, a neural-network-based program generation model conditioned on an encoded set of input-output examples is used to generate a program tree by iteratively expanding a partial program tree, beginning with a root node and ending when all leaf nodes are terminal.

Abstract: In accordance with some embodiments, a method is performed at a device with one or more processors and non-transitory memory. The method includes obtaining location vector data characterizing an object. The method includes determining a neural pose graph associated with a respective time-period based on an initial local pose estimation as a function of respective location vector data. The method includes determining a meta pose estimation associated with the respective time-period by aggregating the neural pose graph associated with the respective time-period and one or more other neural pose graphs associated with one or more temporally adjacent time-periods.

Abstract: A computer-implemented system and method for storing data associated with an agent in a multi-dimensional environment via a memory architecture. The memory architecture is structured so that each unique position in the environment corresponds to a unique position within the memory architecture, thereby allowing the memory architecture to store features located at a particular position in the environment in a memory location specific to that location. As the agent traverses the environment, the agent compares the features at the agent's particular position to a summary of the features stored throughout the memory architecture and writes the features that correspond to the summary to the coordinates in the memory architecture that correspond to the agent's position. The system and method allows agents to learn, using a reinforcement signal, how to behave when acting in an environment that requires storing information over long time steps.

Abstract: Described are systems, methods, and computer-readable media for program generation in a domain-specific language based on input-output examples. In accordance with various embodiments, a neural-network-based program generation model conditioned on an encoded set of input-output examples is used to generate a program tree by iteratively expanding a partial program tree, beginning with a root node and ending when all leaf nodes are terminal.

Abstract: Generally discussed herein are devices, systems, and methods for encoding input-output examples. A method of generating a program using an encoding of input-output examples, may include processing an input example of the input-output examples, using a first long short term memory (LSTM) neural network, one character at a time to produce an input feature vector, processing an output example associated with the input example in the input-output examples, using the LSTM neural network, one character at a time to produce an output feature vector, determining (a) a cross-correlation between the input feature vector and the output feature vector or (b) previously computed feature vectors for a different input-output example that are sufficiently close to the input feature vector and the output feature vector, respectively, and using the determined cross-correlation or previously computed vector, generating a program consistent with the input example and the output example.