摘要：Humans use two distinct cognitive strategies separately to understand and predict other humans' behavior. One is mind-reading, in which an abstract intervening variable such as an intention or an emotional state is assumed to be a source of a variety of behaviors. The other is behavior-reading, in which an actor's superficial behavior is modeled based on a finite set of state-action (stimulus-response) associations. We hypothesize that an actor's ability to generate unlimited behavioral patterns to reach a goal is key for an observer switching between these two cognitive strategies in a competitive situation. We provide support for this hypothesis through two studies using four agents with different appearances. We show that only the agent with a human appearance was thought to possess both the ability to generate a variety of behaviors and internal mental states, such as minds and emotions (Study 1). We also show that humans used mixed (opposing) strategies against the agent with a human appearance and exploitative strategies against the agents with mechanical appearances when they played a repeated zero-sum game (Study 2). Our findings show that humans understand that human behavior is varied; that humans have internal representations, such as minds and emotions; that the behavior of machines is governed by a limited number of fixed rules; and that machines do not possess internal mental states. Our findings also suggest that the function of mind-reading is to trigger a strategy for use against agents with variable behavior and that humans exploit others who lack behavioral variability based on behavior-reading in a competitive situation.
