Self-reorganizing knowledge representation for autonomous learning in social agents

The CIVS (Civilization-Inspired Vying Societies) system is a novel evolutionary learning multi-agent system loosely inspired by the history of human civilization. CIVS uses artificial life (Alife) methods to produce highly-capable artificial intelligence (AI) agents proficient in one or more complex tasks as well as more general adaptability, reasoning, and survivability in dynamic, unpredictable environments. A new cognitive architecture called CHARISMA is proposed as a brain for the social agents within the CIVS system. In this paper, we will develop a self-growing, self-reorganizing semantic network named SHYNE (Semantic HYper NEtwork) as the basic knowledge representation data structure for the CHARISMA cognitive architecture. SHYNE builds on ideas from semantic networks, slipnets, and hypergraphs to create a very powerful and flexible data structure. We believe SHYNE will solve the problem of brittle reliance on predefined rules/relations/concepts with its extensive self-reorganizing capabilities. Experimental results demonstrate that the proposed SHYNE is efficient as the knowledge representation for social agents.