A Sequential Action Generation Framework for Intelligent Agents in Cyberspace

Abstract

Intelligent agents learn their behaviors in games or crowd simulations for diverse behaviors. Given that iterative learning is required to generate behaviors by learning, programming by demonstration (PbD) can be applied to such intelligent agents for reducing learning time. One line of research has focused on how to define portions of sequential actions executed by a predecessor as building blocks of sequential actions to be executed by an intelligent agent. These studies face the following problems: first, the approach to divide collected actions using the variance of actions in consecutive order cannot derive consecutive actions in various ways; and second, the approach deriving consecutive actions in all cases increases the amount of calculation depending on the number of actions. This paper proposes a behavior generation framework that includes functions to reduce the amount of computation to generate a set of behaviors for an intelligent agent. In an experiment applying the framework to a driving simulation, the number of movements was reduced to 24% by filtering movements. In addition, the generated behaviors were reduced to 23% by quantization and filtering. Thus, the amount of calculation required to generate the behaviors was reduced.