Abstract: An agent trained using reinforcement learning (RL) can be used to determine a structure for a complex tensor network. The agent makes incremental changes to a tensor network according to a policy model, where parameters of the policy model were trained using RL. The agent may use a cost function to assess the changes, e.g., to determine whether or not to keep a particular modification. In some cases, tensor networks determined using the RL agent can be used to train a model that can more efficiently select a structure for a complex tensor network.

Abstract: A method and system for providing location based services to a user are provided. Multiple beacons are strategically positioned in predetermined locations in an environment. The beacons encode and project beacon related information. A client application is provided on the user's communication device. The client application captures the beacon related information in one or more communication modes, extracts the captured beacon related information, and sends a request to a service management server for area information and contextual information based on the extracted beacon related information via a communication network. The service management server assembles and transmits area information and contextual information to the communication device based on the sent request from the client application via the communication network.