Learning And Abstraction In Simulation

Abstract

Complex simulation programs typically require large amounts of computation to produce highly detailed output difficult for users to understand . Building abstracted simulation systems that simplify both computation and output can make simulation both more economical and more intelligible . We describe an approach to abstracted simulation that uses a scenario network to represent typical sequences of events in the simulat~on domain. Abstract simulation output is generated by probabilistically determined event-to-event transitions within the network. A learning process determines probabilities and builds up more abstract "chunked" events based on the actual frequency of event sequences in runs of the detailed simulator. The approach is generalizable across domains, and fulfills many of the goals of abstracted simulation: reducing computation, saving resources, filtering information and providing aggregated, intelligible output.