BEHAVIOR LEARNING DEVICE, BEHAVIOR LEARNING METHOD, BEHAVIOR LEARNING SYSTEM, PROGRAM, AND RECORDING MEDIUM

摘要

This behavior learning device has: a behavior candidate acquisition unit that extracts a plurality of available behavior candidates on the basis of situation information data indicating the environment and own situation; a score acquisition unit that acquires a score, which is an index indicating the predicted effect of the result of a behavior, for each of the plurality of behavior candidates; a behavior selection unit that selects, from among the plurality of behavior candidates, the behavior candidate having the highest score; and a score adjustment unit that adjusts the value of the score associated with the selected behavior candidate on the basis of the results of conducting the selected behavior in the environment.