Development of social adaptive agents in simulation game of cross-cultural experience

Recently, researches of human-agent interaction (HAI) are popular toward autonomous agents to act and cope in various human societies. If agents adapt to humans´ society, they have social skills. In this paper, we introduce how developing a social adaptive agent. There are many rules in societies. Therefore, social agents should have a social skill which is obtaining social rules. We develop agents adapting group as social adaptive agents. We improve some functions from a simulation game: Online BARNGA from BARNGA to observe humans´ behavior. We observe humans´ behavior in Online BARNGA. As a result, we find that humans have transitions of three inner states with rdquonoticerdquo and rdquobehaviorrdquo to get implicit rules, and rules fall into two categories: a byelaw and an ethic. In Online BARNGA, a byelaw is a rule of card game, an ethic is a strategy. Based on the above results, we develop agents with transitions of three inner state with rdquonoticerdquo and rdquobehaviorrdquo and two type learning modules. Furthermore, we analyze agents´ behavior in online BARNGA, and compare humans´ that. As a result, we confirm that agent adapt socially as if it were human.