Modelling Diffusion of Dependent and Conflicting Behaviours with Dynamic Logic
Gabriel de Senne Amorim, Marlo Souza, Álvaro Moreira · Frontiers in artificial intelligence and applications · 2024
We propose modeling different policies for behaviour diffusion in a network of agents considering conflict and dependency. In approaches based on the threshold-limited influence model, an agent adopts a behaviour if it has received enough influence from its social connections to surpass a given behaviour threshold. We also consider models where adopting a behaviour might depend on other behaviours and where behaviours might conflict. We assume a network with a fixed structure and undirected and same-weight connections between agents, i.e., a network where, at least in principle, any two agents have the same capacity to influence each other. We propose a minimal propositional dynamic logic language for reasoning about each diffusion policy, and we provide a sound and complete axiomatization for it.