Methods and systems for selecting among multiple concurrently active paths through a network are provided. According to one embodiment, a method is performed by a network interface of a source node within a loop-free, reverse-path-learning network. The network is divided into multiple virtual networks. A packet destined for a destination node and specifying an address for the destination or including information from which the address can be derived is received from the source. A set of virtual networks that can be used to transport the packet from the source node to the destination node is determined. Each virtual network in the set of virtual networks provides a different path through the network from the source to the destination. A particular virtual network from the set of virtual networks is selected, thereby effectively selecting a particular path from multiple selectable paths between the source and the destination.