Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a graph model representing an environment being interacted with by an agent. In one aspect, one of the methods include: obtaining experience data; using the experience data to update a visitation count for each of one or more state-action pairs represented by the graph model; and at each of multiple environment exploration steps: computing a utility measure for each of the one or more state-action pairs represented by the graph model; determining, based on the utility measures, a sequence of one or more planned actions that have an information gain that satisfies a threshold; and controlling the agent to perform the sequence of one or more planned actions to cause the environment to transition from a state characterized by a last observation received after a last action in the experience data into a different state.

Abstract: A system for event prediction using schema networks includes a first antecedent entity state that represents a first entity at a first time; a first consequent entity state that represents the first entity at a second time; a second antecedent entity state that represents a second entity at the first time; and a first schema factor that couples the first and second antecedent entity states to the first consequent entity state; wherein the first schema factor is configured to predict the first consequent entity state from the first and second antecedent entity states.

Abstract: A system and method for machine understanding, using program induction, includes a visual cognitive computer including a set of components designed to execute predetermined primitive functions. The method includes determining programs using a program induction engine that interfaces with the visual cognitive computer to discover programs using the predetermined primitive functions and/or executes the discovered programs based on an input.

Abstract: A hierarchical compositional network, representable in Bayesian network form, includes first, second, third, fourth, and fifth parent feature nodes; first, second, and third pool nodes; first, second, and third weight nodes; and first, second, third, fourth, and fifth child feature nodes.

Abstract: A hierarchical compositional network, representable in Bayesian network form, includes first, second, third, fourth, and fifth parent feature nodes; first, second, and third pool nodes; first, second, and third weight nodes; and first, second, third, fourth, and fifth child feature nodes.

Abstract: A method for robot control using visual feedback including determining a generative model S100, training the generative model S200, and controlling the robot using the trained generative model S300.

Abstract: The method for query training can include: determining a graphical representation, determining an inference network based on the graphical representation, determining a query distribution, sampling one or more train queries from the query distribution, and optionally determining a trained inference network by training the untrained inference network using the train query. The method can optionally include determining an inference query and determining an inference query result for the inference query using the trained inference network.

Abstract: A method for robot control using visual feedback including determining a generative model S100, training the generative model S200, and controlling the robot using the trained generative model S300.

Abstract: The method for query training can include: determining a graphical representation, determining an inference network based on the graphical representation, determining a query distribution, sampling one or more train queries from the query distribution, and optionally determining a trained inference network by training the untrained inference network using the train query. The method can optionally include determining an inference query and determining an inference query result for the inference query using the trained inference network.

Abstract: A method for robot control using visual feedback including determining a generative model S100, training the generative model S200, and controlling the robot using the trained generative model S300.

Abstract: The method for query training can include: determining a graphical representation, determining an inference network based on the graphical representation, determining a query distribution, sampling one or more train queries from the query distribution, and optionally determining a trained inference network by training the untrained inference network using the train query. The method can optionally include determining an inference query and determining an inference query result for the inference query using the trained inference network.

Abstract: A system for event prediction using schema networks includes a first antecedent entity state that represents a first entity at a first time; a first consequent entity state that represents the first entity at a second time; a second antecedent entity state that represents a second entity at the first time; and a first schema factor that couples the first and second antecedent entity states to the first consequent entity state; wherein the first schema factor is configured to predict the first consequent entity state from the first and second antecedent entity states.

Abstract: A system for event prediction using schema networks includes a first antecedent entity state that represents a first entity at a first time; a first consequent entity state that represents the first entity at a second time; a second antecedent entity state that represents a second entity at the first time; and a first schema factor that couples the first and second antecedent entity states to the first consequent entity state; wherein the first schema factor is configured to predict the first consequent entity state from the first and second antecedent entity states.

Abstract: A system for event prediction using schema networks includes a first antecedent entity state that represents a first entity at a first time; a first consequent entity state that represents the first entity at a second time; a second antecedent entity state that represents a second entity at the first time; and a first schema factor that couples the first and second antecedent entity states to the first consequent entity state; wherein the first schema factor is configured to predict the first consequent entity state from the first and second antecedent entity states.

Abstract: A hierarchical compositional network, representable in Bayesian network form, includes first, second, third, fourth, and fifth parent feature nodes; first, second, and third pool nodes; first, second, and third weight nodes; and first, second, third, fourth, and fifth child feature nodes.