Abstract: The techniques disclosed herein enable a machine learning model to learn a termination condition of a sub-task. A sub-task is one of a number of sub-tasks that, when performed in sequence, accomplish a long-running task. A machine learning model used to perform the sub-task is augmented to also provide a termination signal. The termination signal indicates whether the sub-task's termination condition has been met. Monitoring the termination signal while performing the sub-task enables subsequent sub-tasks to seamlessly begin at the appropriate time. A termination condition may be learned from the same data used to train other model outputs. In some configurations, the model learns whether a sub-task is complete by periodically attempting subsequent sub-tasks. If a subsequent sub-task can be performed, positive reinforcement is provided for the termination condition. The termination condition may also be trained using synthetic scenarios designed to test when the termination condition has been met.

Abstract: The techniques disclosed herein enable systems to solve routing problems using machine learning augmented by optimization modules. To plot a route, a system receives a plurality of nodes from a problem space. The plurality of nodes is then analyzed by an optimization module and ranked based on various criteria such as distance from a reference node and deadline. Based on the ranking, the optimization module can select a smaller subset of nodes that is then processed by a machine learning model. The machine learning model can then select a node from the subset of nodes for addition to a route. This process can be repeated until a route is plotted for the full set of nodes within the problem space. In addition, the system can be configured to monitor current conditions of the problem space to modify the route in response to changes.

Abstract: Technologies for reinforcement learning-based optimization of manufacturing lines are disclosed. A reinforcement learning-based selector is trained utilizing reinforcement learning to select a reinforcement learning-based controller for controlling the operation of machines on a manufacturing line. The selection can be made based upon inputs from the machines on the manufacturing line indicating whether machines on the line are jammed, whether the manufacturing line is operating at a steady state, or other conditions. The selected reinforcement learning-based controller can generate outputs to adjust parameters of the machines on the manufacturing line, such as operating speed, in order to recover from the jamming of one or more machines, to transition to a steady state of operation, or to operate the manufacturing line in a steady state of operation. The selector and the reinforcement learning-based controllers can be trained using reinforcement learning on a simulation of the manufacturing line.

Abstract: Methods, systems, and computer programs are presented for scheduling resources used for package delivery. One method includes an operation for initializing a reinforcement learning (RL) agent that calculates staff requirements for performing jobs, each job including a delivery of a package to a respective location. The method further includes training the RL agent by performing a set of iterations. Each iteration includes operations for accessing job data, the job data including jobs for delivery, coordinates for the deliveries, and deadlines for the deliveries; generating clusters in a map for the jobs using unsupervised learning; generating the staff requirements by the RL agent based on feature extraction from the spatial and temporal distribution of the jobs; calculating a reward for the generated staff requirements; and modifying the RL agent using reinforcement learning based on the reward. Further, the trained RL agent is utilized for determining staff requirements for new jobs.

Abstract: An electrochemical cell includes a negative electrode having a first liquid phase having a first active metal, a positive electrode having a second liquid phase having a second active metal, and a liquid electrolyte having a salt of the first active metal and a salt of the second active metal. The electrochemical cell also includes a bipolar faradaic membrane, disposed between the negative electrode and the positive electrode, having a first surface facing the negative electrode and a second surface facing the positive electrode. The bipolar faradaic membrane is configured to allow cations of the first active metal to pass through and to impede cations of the second active metal from transferring from the positive electrode to the negative electrode and is at least partially formed from a material having an electronic conductivity sufficient to drive faradaic reactions at the second surface with the cations of the positive electrode.

Abstract: An electrochemical cell comprising: a negative electrode comprising lithium and aluminum; a positive electrode, separate from the negative electrode, comprising a liquid phase having zinc; a liquid electrolyte, disposed between the negative electrode and the positive electrode, comprising a salt of lithium and a salt of zinc; and a bipolar faradaic membrane, disposed between the negative electrode and the positive electrode, having a first surface facing the negative electrode and a second surface facing the positive electrode, the bipolar faradaic membrane configured to allow cations of lithium to pass through and configured to impede cations of zinc from transferring from the positive electrode to the negative electrode, the bipolar faradaic membrane at least partially formed from a material having an electronic conductivity sufficient to drive faradaic reactions at the second surface with the cations of the positive electrode.

Abstract: An electrochemical cell includes a negative electrode having a first liquid phase having a first active metal, a positive electrode having a second liquid phase having a second active metal, and a liquid electrolyte having a salt of the first active metal and a salt of the second active metal. The electrochemical cell also includes a bipolar faradaic membrane, disposed between the negative electrode and the positive electrode, having a first surface facing the negative electrode and a second surface facing the positive electrode. The bipolar faradaic membrane is configured to allow cations of the first active metal to pass through and to impede cations of the second active metal from transferring from the positive electrode to the negative electrode and is at least partially formed from a material having an electronic conductivity sufficient to drive faradaic reactions at the second surface with the cations of the positive electrode.

Abstract: A cell for high temperature electrochemical reactions is provided. The cell includes a container, at least a portion of the container acting as a first electrode. An extension tube has a first end and a second end, the extension tube coupled to the container at the second end forming a conduit from the container to said first end. A second electrode is positioned in the container and extends out of the container via the conduit. A seal is positioned proximate the first end of the extension tube, for sealing the cell.

Abstract: A cell for high temperature electrochemical reactions is provided. The cell includes a container, at least a portion of the container acting as a first electrode. An extension tube has a first end and a second end, the extension tube coupled to the container at the second end forming a conduit from the container to said first end. A second electrode is positioned in the container and extends out of the container via the conduit. A seal is positioned proximate the first end of the extension tube, for sealing the cell.