The study of social networks has increased rapidly in the past few decades. Of recent interest are the dynamics of changing opinions over a network. Some research has investigated how interpersonal influence can affect opinion change, how to maximize/minimize the spread of opinion change over a network, and recently, if/how agents can act strategically to effect some outcome in the network's opinion distribution. This latter problem can be modeled and addressed as a reinforcement learning problem; we introduce an approach to help network agents find strategies that outperform hand-crafted policies. Our preliminary results show that our approach is promising in networks with dynamic topologies.

As research into the dynamics and properties of opinion diffusion on social networks has increased, so too has the attention paid to modeling such systems. Simulations using agent-based modeling (ABM) analyze aggregate network outcomes when individual agents act on typically limited information, and tend to focus on agents that are conforming and homophilic - that is, they prefer to be around similar others, and they update their own personal state over time to be more like their friends. In this work, we illustrate the value of diverse agent modeling in environments that allow for strategic unfriending. We focus on network dynamics generated by three agent models, or archetypes. Our work shows that polarization and consensus dynamics, as well as topological clustering effects, may rely more than previously known on the interplay between individuals' goals for the composition of their neighborhood's opinions.