Synthesising Evolutionarily Stable Normative Systems
Javier Morales, Michael Wooldridge, Juan A. Rodr\'iguez-Aguilar and, Maite L\'opez-S\'anchez

TL;DR
This paper introduces an evolutionary game theory-based framework for synthesising normative systems in multi-agent environments, ensuring coordination and rational norm adoption, validated through traffic domain simulations.
Contribution
It presents a novel evolutionary approach for synthesising effective and rational normative systems in multi-agent coordination tasks.
Findings
Successfully synthesised norms that promote coordination
Normative systems that agents are likely to adopt
Effective in simulated traffic scenarios
Abstract
Within the area of multi-agent systems, normative systems are a widely used framework for the coordination of interdependent activities. A crucial problem associated with normative systems is that of synthesising norms that effectively accomplish a coordination task and whose compliance forms a rational choice for the agents within the system. In this work, we introduce a framework for the synthesis of normative systems that effectively coordinate a multi-agent system and whose norms are likely to be adopted by rational agents. Our approach roots in evolutionary game theory. Our framework considers multi-agent systems in which evolutionary forces lead successful norms to prosper and spread within the agent population, while unsuccessful norms are discarded. The outputs of this evolutionary norm synthesis process are normative systems whose compliance forms a rational choice for 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 · Experimental Behavioral Economics Studies · Game Theory and Applications
