让AI通过共情机制自发产生助人行为
Empathic Coupling of Homeostatic States for Intrinsic Prosociality
- 用生理稳态模型模拟智能体自我调节，引入共情机制
- 只有当伙伴痛苦影响自身状态时，才会出现助人行为
- 揭示情感共情在人工代理中促发利他行为的关键作用
当面对他人苦难时，我们常感到自身不适并产生帮助冲动。受生命系统启发，我们研究自主智能体在以维持自身稳态为动机时，如何自发产生利他行为。通过多智能体强化学习，将每个智能体视为易受伤害的稳态调节器。引入类共情机制：智能体可‘观察’伙伴内部状态（认知共情），或直接与伙伴状态耦合（情感共情）。在三个简单多智能体环境中，仅当伙伴的困境直接影响自身稳态时，利他行为才出现。研究明确了人工智能体中利他行为所需的共情类型与作用机制。
原文摘要 · Abstract (English)
When regarding the suffering of others, we often experience personal distress and feel compelled to help. Inspired by living systems, we investigate the emergence of prosocial behavior among autonomous agents that are motivated by homeostatic self-regulation. We perform multi-agent reinforcement learning, treating each agent as a vulnerable homeostat charged with maintaining its own well-being. We introduce an empathy-like mechanism to share homeostatic states between agents: an agent can either \emph{observe} their partner's internal state (cognitive empathy) or the agent's internal state can be \emph{directly coupled} to that of their partner's (affective empathy). In three simple multi-agent environments, we show that prosocial behavior arises only under homeostatic coupling - when the distress of a partner can affect one's own well-being. Our findings specify the type and role of empathy in artificial agents capable of prosocial behavior.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。