How can individual agents coordinate their actions to achieve a shared objective in distributed systems? This challenge spans economic, technical, and sociological domains, each confronting scalability, heterogeneity, and conflicts between individual and collective goals. In economic markets, a common currency facilitates coordination, raising the question of whether such mechanisms can be applied in other contexts. This paper explores this idea within social media platforms, where social support (likes, shares, comments) acts as a currency that shapes content production and sharing. We investigate two key questions: (1) Can social support serve as an effective coordination tool, and (2) What role do influencers play in content creation and dissemination? Our formal analysis shows that social support can coordinate user actions similarly to money in economic markets. Influencers serve dual roles, aggregating content and acting as information proxies, guiding content producers in large markets. While imperfections in information lead to a "price of influence" and suboptimal outcomes, this price diminishes as markets grow, improving social welfare. These insights provide a framework for understanding coordination in distributed environments, with applications in both sociological systems and multi-agent AI systems.

It has been experimentally shown that communities in social networks tend to have a core-periphery topology. However, there is still a limited understanding of the precise structure of core-periphery communities in social networks including the connectivity structure and interaction rates between agents. In this paper, we use a game-theoretic approach to derive a more precise characterization of the structure of core-periphery communities.

Peter Dayan E25-210, MIT Cambridge, MA 02139 We provide a model of the standard watermaze task, and of a more challenging task involving novel platform locations, in which rats exhibit one-trial learning after a few days of training. The model uses hippocampal place cells to support reinforcement learning, and also, in an integrated manner, to build and use allocentric coordinates. 1 INTRODUCTION

We provide a model of the standard watermaze task, and of a more challenging task involving novel platform locations, in which rats exhibit one-trial learning after a few days of training. The model uses hippocampal place cells to support reinforcement learning, and also, in an integrated manner, to build and use allocentric coordinates. 1 INTRODUCTION

We provide a model of the standard watermaze task, and of a more challenging task involving novel platform locations, in which rats exhibit one-trial learning after a few days of training. The model uses hippocampal place cells to support reinforcement learning, and also, in an integrated manner, to build and use allocentric coordinates. 1 INTRODUCTION