Behavioral self-organization in lifelike agents

This paper is concerned with the acquisition of behaviors in lifelike synthetic agents that interact with virtual graphical environments. The goal of the agent behavioral acquisition is to select an effective behavioral pattern that adapts to the conditions of the agent environment, and in addition, to determine the corresponding behavioral parameters. In doing so, the lifelike agents will employ a dual-level behavioral self-organizing (BSo) approach, in which the high-level acquires a conditioned association from the presently sensed state of the environment to the requirement of a desired motion as well as a plausible behavioral pattern to enable such a motion, whereas the low-level computes the optimal parameters for the identified behavior in fulfilling the motion requirement.