A computing system for performing distributed large scale reinforcement learning with improved efficiency can include a plurality of actor devices, wherein each actor device locally stores a local version of a machine-learned model, wherein each actor device is configured to implement the local version of the machine-learned model at the actor device to determine an action to take in an environment to generate an experience, a server computing system configured to perform one or more learning algorithms to learn an updated version of the machine-learned model based on the experiences generated by the plurality of actor devices, and a hierarchical and distributed data caching system including a plurality of layers of data caches that propagate data descriptive of the updated version of the machine-learned model from the server computing system to the plurality of actor devices to enable each actor device to update its respective local version of the model.

A computing system for performing distributed large scale reinforcement learning with improved efficiency can include a plurality of actor devices, wherein each actor device locally stores a local version of a machine-learned model, wherein each actor device is configured to implement the local version of the machine-learned model at the actor device to determine an action to take in an environment to generate an experience, a server computing system configured to perform one or more learning algorithms to learn an updated version of the machine-learned model based on the experiences generated by the plurality of actor devices, and a hierarchical and distributed data caching system including a plurality of layers of data caches that propagate data descriptive of the updated version of the machine-learned model from the server computing system to the plurality of actor devices to enable each actor device to update its respective local version of the model.

Systems and methods for producing a neural network architecture with improved energy consumption and performance tradeoffs are disclosed, such as would be deployed for use on mobile or other resource-constrained devices. In particular, the present disclosure provides systems and methods for searching a network search space for joint optimization of a size of a layer of a reference neural network model (e.g., the number of filters in a convolutional layer or the number of output units in a dense layer) and of the quantization of values within the layer. By defining the search space to correspond to the architecture of a reference neural network model, examples of the disclosed network architecture search can optimize models of arbitrary complexity. The resulting neural network models are able to be run using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art, mobile-optimized models.

Systems and methods for producing a neural network architecture with improved energy consumption and performance tradeoffs are disclosed, such as would be deployed for use on mobile or other resource-constrained devices. In particular, the present disclosure provides systems and methods for searching a network search space for joint optimization of a size of a layer of a reference neural network model (e.g., the number of filters in a convolutional layer or the number of output units in a dense layer) and of the quantization of values within the layer. By defining the search space to correspond to the architecture of a reference neural network model, examples of the disclosed network architecture search can optimize models of arbitrary complexity. The resulting neural network models are able to be run using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art, mobile-optimized models.

A system and method for providing real-time distributed micro-grid optimization using price signals to the electrical grid system by allowing bi-directional electricity usage from a distributed network of energy storage stations to form a large, distributed resource for the grid. A machine learning optimization module ingests various forms of data-from grid telemetry to traffic data to trip-to-trip data and more-in order to make informed spatiotemporal decisions about optimal pricing signals as well as strategically placing and balancing energy stores across various regions to support optimum energy usage, risk mitigation, grid fortification, and revenue generation. Energy stores are then sent updated price signals and updated parameters as to the amount of energy to hold or release.

A method and apparatus for training an information adjustment model of a charging station, an electronic device, and a storage medium are provided. An implementation comprises: acquiring a battery charging request, and determining environment state information corresponding to each charging station in a charging station set; determining, through an initial policy network, target operational information of each charging station in the charging station set for the battery charging request, according to the environment state information; determining, through an initial value network, a cumulative reward expectation corresponding to the battery charging request according to the environment state information and the target operational information; training the initial policy network and the initial value network by using a deep deterministic policy gradient algorithm; and determining the trained policy network as an information adjustment model corresponding to each charging station.

A method for performing an at least partially automatic vehicle function of a vehicle depending on a travel route to be assessed by means of a driver assistance system is disclosed. The method comprises providing a plurality of clusters from route data with respect to at least one known travel route, wherein the clusters group the route data sectionwise according to predefined geometric parameters. The method comprises providing recorded course data that indicate a course of the travel route to be assessed and applying the clusters to the course data in order to divide the travel route to be assessed into route sections corresponding to the clusters. The method comprises determining at least one uncertainty quantity which is characteristic of an uncertainty with respect to the assignment made and determining a control quantity as a function of the uncertainty quantity and providing the control quantity for performing the vehicle function.

A method for performing an at least partially automatic vehicle function of a vehicle depending on a travel route to be assessed by means of a driver assistance system is disclosed. The method comprises providing a plurality of clusters from route data with respect to at least one known travel route, wherein the clusters group the route data sectionwise according to predefined geometric parameters. The method comprises providing recorded course data that indicate a course of the travel route to be assessed and applying the clusters to the course data in order to divide the travel route to be assessed into route sections corresponding to the clusters. The method comprises determining at least one uncertainty quantity which is characteristic of an uncertainty with respect to the assignment made and determining a control quantity as a function of the uncertainty quantity and providing the control quantity for performing the vehicle function.

A computer implemented method for determining at least one target parameter set for a flow chemistry setup (110) for flow chemistry in slugs is disclosed. The method is a self-learning method. The method comprises the following steps: a) determining at least one process variable by using at least one sensor (122) of a flow chemistry setup (110); b) training of at least one machine-learning model (126) based on the process variable; c) determining the target parameter set by applying an optimizing algorithm in terms of at least one optimization target on the trained machine-learning model (126); d) providing the determined target parameter set and/or considering the determined target parameter set for evaluating a flow chemistry setup (110) and/or for evaluating at least one flow chemistry product.

A computer implemented method for determining at least one target parameter set for a flow chemistry setup (110) for flow chemistry in slugs is disclosed. The method is a self-learning method. The method comprises the following steps: a) determining at least one process variable by using at least one sensor (122) of a flow chemistry setup (110); b) training of at least one machine-learning model (126) based on the process variable; c) determining the target parameter set by applying an optimizing algorithm in terms of at least one optimization target on the trained machine-learning model (126); d) providing the determined target parameter set and/or considering the determined target parameter set for evaluating a flow chemistry setup (110) and/or for evaluating at least one flow chemistry product.