2024/11/16 by Naoto Yoshida, Yoshida, Naoto, Kingson Man +1 · 3 citations
Psychology · Social Sciences · #Action Observation and Synchronization #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Language and cultural evolution #Multiagent Systems (cs.MA) #Neural and Evolutionary Computing (cs.NE) #Social Robot Interaction and HRI
paper · pdf · doi:10.48550/arxiv.2412.12103
openalex publication_date 2024/11/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 observe their partner's internal state (cognitive empathy) or the agent's internal state can be 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.