Exploration enhances cooperation in the multi-agent communication system
Zhao Song, Chen Shen, Zhen Wang, The Anh Han

TL;DR
This paper demonstrates that incorporating strategic exploration into multi-agent communication protocols significantly enhances cooperation, revealing an optimal exploration rate that balances stability and alliance formation.
Contribution
It introduces a novel two-stage evolutionary game model that explicitly includes exploration, showing how strategic randomness promotes cooperation in multi-agent systems.
Findings
Optimal exploration rate maximizes cooperation
Moderate exploration destabilizes defection
Balance between oscillation and amplification enables cooperation peak
Abstract
Designing protocols enhancing cooperation for multi-agent systems remains a grand challenge. Cheap talk, defined as costless, non-binding communication before formal action, serves as a pivotal solution. However, existing theoretical frameworks often exclude random exploration, or noise, for analytical tractability, leaving its functional impact on system performance largely unexplored. To bridge this gap, we propose a two-stage evolutionary game-theoretical model, integrating signalling with a donation game, with exploration explicitly incorporated into the decision-making. Our agent-based simulations across topologies reveal a universal optimal exploration rate that maximises system-wide cooperation. Mechanistically, moderate exploration undermines the stability of defection and catalyses the self-organised cooperative alliances, facilitating their cyclic success. Moreover, the…
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
TopicsEvolutionary Game Theory and Cooperation · Modular Robots and Swarm Intelligence · Reinforcement Learning in Robotics
