Empathic Coupling of Homeostatic States for Intrinsic Prosociality
This addresses the problem of designing artificial agents with intrinsic prosociality for multi-agent systems, though it is incremental as it builds on existing reinforcement learning and empathy concepts.
The study investigated how autonomous agents develop prosocial behavior by using homeostatic self-regulation and empathy-like mechanisms, showing that prosocial actions only occur when agents' internal states are directly coupled, affecting their own well-being.
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.