Framework for Modeling Partial Conceptual Autonomy of Adaptive and Communicating Agents
Timo Honkela, Tarja Knuuttila · eScholarship (California Digital Library) · 2003
We develop a framework for discussing the degree of conceptual autonomy of natural and artificial agents. We claim that aspects related to learning and communication necessitate adaptive agents that are partially autonomous. We demonstrate how partial conceptual autonomy can be obtained through a self-organization process. The input for the agents consists of perceptions of the environment, expressions communicated by other agents as well as the recognized identities of other agents. Agents and Communication Agents communicate by sending and receiving messages. In the primitive case, all the agents share a common model of their environment (which implies