Abstract: A traffic control system for controlling traffic at a junction includes an intelligent traffic control agent. The intelligent traffic control agent is training using reinforcement learning, in a simulation model of the junction. The simulation model is calibrated and validated preferably using data from the same sensors which are used as inputs to the traffic control agent when deployed to control traffic at the junction.

Abstract: A traffic control system for controlling traffic at a junction includes an intelligent traffic control agent. The intelligent traffic control agent is training using reinforcement learning, in a simulation model of the junction. The simulation model is calibrated and validated preferably using data from the same sensors which are used as inputs to the traffic control agent when deployed to control traffic at the junction.

Abstract: A method can include receiving well plan information that includes a reservoir target associated with a reservoir of a subterranean environment; based at least in part on characteristics of the subterranean environment, determining well trajectory metrics that comprise a geometrical metric; determining a weighted metric based at least in part on weighting of the well trajectory metrics; and, based at least in part on an assessment of the weighted metric, outputting directional drilling information for a well trajectory to the reservoir target.

Abstract: A method can include receiving well plan information that includes a reservoir target associated with a reservoir of a subterranean environment; based at least in part on characteristics of the subterranean environment, determining well trajectory metrics that comprise a geometrical metric; determining a weighted metric based at least in part on weighting of the well trajectory metrics; and, based at least in part on an assessment of the weighted metric, outputting directional drilling information for a well trajectory to the reservoir target.