Gossip helps agents share reputation to boost cooperation and sustainability
Gossip Agents: Reputation through Opinion Dynamics over Evolving Networks
Multiagent Systems
Summary
Many situations involve self-interested agents who need to cooperate, and knowing others' reputations can help. The authors study how agents share opinions about others through gossip in changing networks, where communication depends on location and connections. They show that how widely agents share reputations affects cooperation and leads to better group outcomes, including more peaceful and sustainable behavior in environments where agents move and interact. This approach helps agents decide whom to trust based on both personal experience and shared information.
What this means in practice
- •For social network designers: Design communication rules that control how reputation spreads to promote cooperation in online communities.
- •For multi-robot system developers: Create coordination protocols for robot teams that use gossip-based reputation sharing to improve collective task success and avoid conflicts.
Authors
Yutong Wu, Arlei Silva
Abstract
Sustained cooperation among self-interested learning agents is essential in many shared environments. Reputation systems are among the best-studied mechanisms for promoting such cooperation. Existing multi-agent reinforcement learning approaches, however, typically assume that reputation is either globally available to all agents or derived solely from an agent's own observations, leaving largely unexplored how reputational information propagates between agents. We study gossip, the exchange of information about third parties, as a mechanism for reputation diffusion over dynamic communication networks. Agents form private opinions from limited observations and exchange them with their neighbors following DeGroot opinion dynamics, while the communication network changes as agents interact and move. A tunable broadcast radius controls the reach of information, spanning private reputation, local gossip, and globally shared reputation. We study this framework in two \(n\)-player social dilemmas with distinct network dynamics: a Prisoner's Dilemma with randomly resampled interaction groups and Harvest, where communication neighborhoods emerge from agents' movements. Our results show that the reach of reputational information shapes cooperation in both environments. Moreover, in Harvest, reputation diffusion increases environmental rewards and leads to more peaceful and sustainable behavior.