Abstract
Neurophysiology has revealed the existence of mirror neurons in brains of macaque monkeys and they shows similar activities during executing and observation of goal directed movements performed by self and other. The concept of the mirror neurons/systems is very interesting and suggests that behavior acquisition and recognition of observed behavior are closely related to each other. That is, the behavior learning modules might be used not only for behavior acquisition/execution but also for the understanding of the behavior/intention of other. We propose a novel method not only to learn and execute a variety of behavior but also to understand behavior of others supposing that the observer has already acquired the utilities (state values in reinforcement learning scheme) of all kinds of behavior the observed agent can do. The method does not need a precise world model or coordination transformation system to deal with view difference caused by different viewpoints. This paper shows that an observer can understand/recognize a behavior of other not by precise object trajectory in allocentric/egocentric coordinate space but by estimated utility transition during the observed behavior.
