Homeostatic Coupling for Prosocial Behavior
Naoto Yoshida, Kingson Man

TL;DR
This paper explores how prosocial behavior can emerge among autonomous agents through homeostatic self-regulation and empathy-like mechanisms, showing that shared distress influences helping behaviors in multi-agent reinforcement learning environments.
Contribution
It introduces a novel homeostatic coupling framework and demonstrates that empathy can be learned, leading to prosocial behaviors in autonomous agents.
Findings
Prosocial behavior arises only with homeostatic coupling.
Agents can learn to decode and infer partners' internal states.
Empathy enhances prosocial responses in multi-agent settings.
Abstract
When regarding the suffering of others, we often experience personal distress and feel compelled to help\footnote{Preprint. Under review.}. 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 ({\bf cognitive empathy}) or the agent's internal state can be \emph{directly coupled} to that of their partner ({\bf 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.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Text Analysis Techniques · Opinion Dynamics and Social Influence · Mental Health Research Topics
