Abstract: In some implementations, a method performed by data processing apparatuses includes receiving order data that represents a plurality of ordered items for delivery to a location; selecting a first policy from a store of first policies; transforming at least a portion of the order data into a plurality of item units, based on rules associated with the selected first policy; selecting a second policy from a store of second policies; for each item unit, based on rules associated with the selected second policy, modifying the item unit to include annotated information that corresponds to operations to be performed on the item unit; and generating instructions for grouping the plurality of item units for delivery to the location, based on the annotated information for the item units.

Abstract: In some implementations, a method performed by data processing apparatuses includes receiving order data that represents a plurality of ordered items for delivery to a location; selecting a first policy from a store of first policies; transforming at least a portion of the order data into a plurality of item units, based on rules associated with the selected first policy; selecting a second policy from a store of second policies; for each item unit, based on rules associated with the selected second policy, modifying the item unit to include annotated information that corresponds to operations to be performed on the item unit; and generating instructions for grouping the plurality of item units for delivery to the location, based on the annotated information for the item units.

Abstract: In some implementations, a method performed by data processing apparatuses includes receiving order data that defines one or more orders for items to be transported, selecting a first combination of policies for a plurality of sub-processes, each policy representing a strategy for performing a respective sub-process included in an overall process for transporting the items, performing a first simulation based on the first selected policy combination, selecting a second, different combination of policies for the plurality of sub-processes, performing a second simulation based on the second selected policy combination, comparing results of the first simulation and results of the second simulation, and based on the comparison, selecting one of the first combination of policies or the second combination of policies as an optimized policy combination.